Recommendation
-
TSPORec: Token Selection via Preference Optimization for LLM-Based Sequential Recommendation
2026-08-10 13:47:46Wenqiao Zhu, Chao Xu, Haipang Wu, Ji LiuAbstract
Large Language Models (LLMs) have emerged as powerful tools for improving recommendation systems. The effectiveness of LLMs arises from their ability to harness rich textual information and their capacity to model heterogeneous user preferences based on users' interaction history. However, due to the large-scale and deep architectures, LLM-based sequential recommendation approaches generally incur high inference costs, resulting in a low return on investment. To mitigate this cost, many existing approaches resort to using only the first few tokens of item descriptions, which inadvertently discards valuable information contained in the full text, thereby leading to suboptimal recommendation performance. To address this limitation, we propose a novel Token Selection approach for Preference Optimization in LLM-based sequential Recommendation, i.e., TSPORec, which accurately pinpoints informative tokens throughout the entire textual content to improve recommendation performance. Specifically, we design a three-stage pipeline to select informative tokens and introduce a novel proxy reward to facilitate the implementation. TSPORec not only enhances recommendation performance but also improves computational efficiency. Extensive experiments across two models and datasets demonstrate the superb performance (up to 31.25%) and efficiency (up to 63.4%) of our approach compared with six baseline approaches. Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2608.09605
PDF
-
CoRCi: Cross-Reconstruction of Coherent Interests Modeling in Cross-Domain Sequential Recommendation
2026-08-10 13:15:55Qingtian Bian, Tieying Li, Marcus de Carvalho, Jiaxing Xu, Hui Fang, Yiping KeAbstract
Cross-Domain Sequential Recommendation (CDSR) aims to alleviate data sparsity by transferring dynamic user interests across related domains. A key challenge lies in effectively bridging these domains. In single-domain modeling, models cannot distinguish between domain-specific and domain-invariant interests. Recent methods merge domain-specific sequences chronologically into a mixed-domain sequence to capture domain-invariant knowledge. However, they typically deploy separate encoders for the mixed-domain sequence and train them with per-domain loss aggregation. This workflow magnifies inter-domain discrepancies and disrupts domain-invariant interest coherence, especially when query target pairs in Seq2Seq originate from different domains. In this paper, we present CoRCi (Cross-Reconstruction for Coherent Interest), a dual-target CDSR framework that tackles these drawbacks. Specifically, CoRCi proposes a Cross-Reconstruction approach that generates mixed-domain representations directly from pre-encoded specific-domain representations via cross-attention. The generated representations are then trained using a single, sequence-level, domain-agnostic loss to preserve the coherence of domain-invariant interests. To further suppress domain discrepancies in mixed-domain modeling, CoRCi introduces FocalNCE, which embeds Focal Loss into the preceding mixed-domain InfoNCE objective. The new loss assigns higher penalties to negatives drawn from the same domain as the query, thereby strengthening domain-invariant alignment. Extensive experiments on four real-world datasets demonstrate that CoRCi consistently outperforms state-of-the-art CDSR counterparts, achieving statistically significant gains across all metrics.
Abstract (translated)
URL
https://arxiv.org/abs/2608.09580
PDF
-
Finding the Signal in the Spam: Jointly Learning Rewards and Worker Reliability from Pairwise Comparisons
2026-08-10 13:01:48Kaustubh Shivshankar Shejole, Tanish Agarwal, Arpit Agarwal, Avishek GhoshAbstract
The problem of learning from pairwise comparisons has been widely studied across many domains such as recommendation systems, social choice, and more recently, fine-tuning large language models. In this problem, the goal is to learn item rewards based on pairwise comparisons between them. In many scenarios, these comparisons are elicited from crowdworkers using platforms such as Amazon Mechanical Turk, Scale AI, etc. However, crowdworkers are often unreliable due to limited domain knowledge or revenue-maximizing (spamming) behavior. In this work, our goal is to understand whether worker reliability (competency) can be learned jointly with item rewards. To this end, we adopt the Boltzmann-rational model for pairwise comparisons, which extends the Bradley-Terry-Luce model by incorporating worker competencies. We derive an EM-based algorithm for learning under this model by introducing Polya-Gamma latent variables to transform the logistic likelihood into a conditionally Gaussian form, enabling tractable optimization and leading to a simplified $Q$ function in the E-step of the algorithm. This technique allows us to reduce our formulation to a matrix sensing problem, using which we establish theoretical convergence guarantees for our algorithm. We conduct extensive experiments on real-world and synthetic datasets. These experiments demonstrate the advantages of using our algorithm over several baselines and confirm its strong robustness to both spammers and adversarial workers, highlighting its practical effectiveness in realistic crowdsourcing and reward learning settings. The code and data is publicly available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2608.10045
PDF
-
Coupled Graph--Policy Distillation for Personalized Medication Safety in Older Adults with Multimorbidity
2026-08-10 11:19:44Zihan Wang, Anglin Liu, Rongyi Wang, Dantong Li, Yi Lu, Siqing Yuan, Hongxia Xu, Zhongtian Long, Jintai ChenAbstract
Large language model (LLM) agents can support medication review between clinical visits, but safe choices for older adults with multimorbidity depend on conditions, medications, and geriatric risks that users may omit. We introduce ATLAS, a coupled graph--policy distillation framework for patient-adaptive medication safety. ATLAS structures guideline evidence as a medication-safety graph. Targeted questions update the patient state and distill relevant relations into a patient-specific medication conflict graph (PMCG). A risk-first multi-agent policy uses the PMCG to screen contraindications, assess cautions and monitoring needs, identify safer alternatives, and verify the final medication plan. We also introduce GeriMedBench, an interactive benchmark that tests safety-critical information acquisition and evidence-based decision revision. Across a European non-interactive multimorbidity benchmark, an Asian interactive multimorbidity benchmark, and an Asian non-interactive cross-guideline benchmark, ATLAS achieves the strongest complete-decision performance among the compared systems. On the European non-interactive multimorbidity benchmark, it exceeds the strongest proprietary LLM baseline by 53.73 points in Strict Success Rate and 14.63 points in overall safety reasoning score (OSRS), with no unsafe recommendations under the automated evaluator. A blinded clinician evaluation gives ATLAS higher mean ratings across all five criteria and flags potentially unsafe recommendations in one ATLAS case and two Gemini cases.
Abstract (translated)
URL
https://arxiv.org/abs/2608.09443
PDF
-
Is the ACL Responsible NLP Checklist a Box-Ticking Exercise? A Large-Scale Analysis of EMNLP 2025
Abstract
Responsible NLP practice includes a) transparency, b) ethics, and c) societal impacts. The Responsible NLP Checklist aims to push these goals, and promote responsible practice. Recently, ACL released the EMNLP 2025 Checklists to aid transparency on the current research practice, which we focus on. We curate and release the first two datasets of: a) all the checklist responses and justifications from the EMNLP 2025 Main and Finding tracks; b) checklist reference linking to paper sections. We also provide the first analysis of recent EMNLP Checklists, by examining $73,922$ responses and justifications to them. For the Main track, we find that authors isolate ethics questions of the Checklist from the paper's bulk, mimicking the trend of ethics being an afterthought. We then examine \texttt{NO} responses. We find $44.9\%$ of justifications are poor or bad-faith, being brief or empty. Then, we find significant issues with the checklist design and effort of authors, namely that $6\%$ of all checklists contained logical contradictions between parent and child responses. We also find evidence of surface compliance for responsible ethics, with $53\%$ authors dismissing potential risks or social impacts of their work, for which there should be none. We compare this to the Findings track, noticing a similar trend in both tracks. Lastly, we discuss the implications of the checklist design and provide recommendations for future checklist iterations. Including: a) enforcing a minimum word count, b) enforcing more scrutiny on the risks of appliances.
Abstract (translated)
URL
https://arxiv.org/abs/2608.09280
PDF
-
How People Evaluate AI-, Expert-, and Peer-Style Financial Advice
2026-08-10 02:19:03Aryan Ramchandra Kapadia, Eshwar Chandrasekharan, Koustuv SahaAbstract
As generative AI increasingly becomes a common source of daily decision-making, including financial choices, it is critical to understand how people evaluate AI-generated financial advice. We conducted a preregistered vignette experiment (N = 285) in which substantive financial content---including facts, numerical values, recommendation direction, and core reasoning---was held constant while communication style varied across AI Financial Assistant (AI), Certified Financial Planner (Expert), and Online Community Forum (OC) advice. Displayed source attribution was independently manipulated through correctly labeled, unlabeled, and mislabeled conditions, allowing us to separate attribution effects from source-specific communication cues. Expert advice was rated more favorably than AI advice on 9 of 10 outcomes (|d|=0.20--0.47), and this advantage remained visible without source labels, where Expert advice outperformed AI advice on 8 of 10 outcomes (up to d=0.60). Correct labels added limited differentiation, whereas mislabeling increased ratings of AI advice for situational fit and overall quality (d=0.42 for each) and attenuated the Expert advantage in situational fit (d=-0.36). Descriptive analyses further showed that AI advice was most responsive to displayed attribution and, conversely, that advice-style differences were most visible under an AI label. These findings show that financial-advice evaluations are shaped jointly by displayed attribution and message-level communication cues. We position disclosure not as a neutral transparency mechanism, but as an interpretive frame whose accuracy and interaction with message cues can shape trust and reliance.
Abstract (translated)
URL
https://arxiv.org/abs/2608.09019
PDF
-
GALA: Graph-Augmented LLM Agents for Root Cause Analysis and Incident Response in Microservices
2026-08-10 00:15:07Yifang Tian, Yaming Liu, Zichun Chong, Zihang Huang, Yiran Li, Hans-Arno JacobsenAbstract
Microservice root cause analysis (RCA) requires correlating failures across heterogeneous telemetry within complex service dependency graphs. Existing methods often rely on a single telemetry modality; recent LLM-based approaches can suffer from unconstrained exploration and hallucination; and most systems stop at fault ranking without producing actionable incident response. We present GALA+, a graph-augmented LLM agentic framework centered on graph-guided investigation, which uses service dependencies to bound exploration and refine diagnosis through localized multi-modal evidence. For initial hypothesis generation, GALA+ combines complementary telemetry signals with STRIX, a novel trace- and graph-structure-aware scoring module. GALA+ then produces ranked diagnoses, incident summaries, and stratified action recommendations. We further introduce SURE-Score, a human-guided evaluation framework co-developed with industry SRE experts for assessing RCA-specific output quality beyond conventional text similarity metrics. On two microservice benchmarks, GALA+ consistently achieves the strongest overall results, surpassing the best LLM-based baseline by more than 25 percentage points in AC@1, while also receiving the highest ratings from both SURE-Score and independent human SRE evaluation.
Abstract (translated)
URL
https://arxiv.org/abs/2608.08968
PDF
-
LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning Routing
2026-08-09 20:02:44Juncheng Dong, Ding Tong, Ishan Gupta, Yuyan WangAbstract
Recommendation systems thrive on personalization, where ''correctness'' is rarely a binary truth but a matter of subjective human preference. As Large Language Models (LLMs) are deployed as autonomous verifiers of safety and quality guidelines, they face a distinctive challenge: context-aware preference alignment. Recent gains in Reinforcement Learning with Verifiable Rewards (RLVR) are indexed mostly on objective, mathematical tasks. Through a large-scale study spanning both proprietary and open-source models on four real-world verification tasks from a production recommender platform, we ask whether explicit reasoning generalizes to subjective, human-centric industry rubrics. We expose a fundamental vulnerability: rigid, math-centric reasoning traces actively degrade verification, and applying standard RLVR triggers a phenomenon we term reasoning collapse, in which the policy abandons deliberation in favor of rapid heuristic guessing. We introduce a conditional length-penalized post-training algorithm that intertwines verification accuracy with bounded reasoning length, halting collapse and recovering performance. Finally, we show that a reasoning trace's efficacy is tightly coupled with its socio-linguistic framing: across 1500 synthesized personas, verification accuracy swings by nearly 0.38 macro-F1 depending solely on the adopted reasoning persona---evidence that much subjective-verification error is really reasoning-style mismatch. This observation motivates a mid-training architecture that routes reasoning through contextually aligned personas. This work offers both a scalable algorithmic patch and a long-term architectural blueprint for aligning reasoning models with real-world subjective constraints.
Abstract (translated)
URL
https://arxiv.org/abs/2608.08889
PDF
-
UniMoMo: Expert Merging-Based MoE Acceleration for Large Recommendation Models
2026-08-09 10:20:20Lei Xin, Bin Gu, Peize Li, Zitong Wang, Jianbo Zhao, Changjiang Jiang, Yanyue Xie, Chao Huang, Xuyang Zhao, Zunhai Su, Fanhu Zeng, Zhenglun KongAbstract
Sparse mixture-of-experts (MoE) layers expand recommendation capacity through conditional computation, yet a trained checkpoint still stores and routes over its full expert bank. We study a deployment problem: convert that checkpoint to a smaller standard MoE under an explicit expert budget, without adding a compression-specific online module. To address this, we introduce UniMoMo, a post-training compression framework formulated as a constrained graph coarsening problem. Rather than relying on parameter distance, UniMoMo groups experts based on their functional similarity, using an unlabeled calibration set to measure how similarly experts respond to shared recommendation states. To prevent performance degradation, we introduce a layer-adaptive protection mechanism that restricts the merging of high-traffic experts based on their routing exposure. Across Amazon Beauty, KuaiRec, and TenRec with 2, 4, and 6 MoE blocks, the final four-expert checkpoints obtain source-relative five-run mean NDCG@10 ratios of 99.92%--102.30% and measured A100 speedups of 1.28$\times$--1.63$\times$. An aggressive two-expert, top-1 operating point obtains ratios of 98.36%--104.24% and speedups of 1.47$\times$--2.21$\times$. These endpoint results evaluate the complete conversion-and-adaptation workflow and show that a trained recommendation MoE can be exported at multiple serving budgets.
Abstract (translated)
URL
https://arxiv.org/abs/2608.08627
PDF
-
Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders
2026-08-08 18:32:34Chan Aristella Lu, Arya Fayyazi, Junhao Zhang, Saeid Shokoufa, Yue Xing, Zhen Xiang, Kyu Hyung Lee, Mehdi Kamal, Massoud PedramAbstract
Fairness audits for LLM-based recommenders have largely focused on observable outputs, implicitly assuming that stable recommendations reflect stable internal processing. We challenge this assumption with FairGap, the first benchmark to jointly evaluate recommendation fairness at two levels: observable output shift (OBS) and hidden representation shift (IBS), measured through controlled counterfactual identity probes across gender, age, and race. Their relationship is summarized via Representation-Output Alignment (ROA), with quadrant diagnostics for identifying user-level hidden-output mismatch. Applied to six open-weight LLM families across three domains, FairGap reveals pervasive hidden-output decoupling: ROA rarely exceeds 0.22, and a non-negligible user population shows stable outputs despite substantial internal shifts, a mode that output-only audits cannot detect by design. Further, activation steering that reduces IBS by up to 8x simultaneously worsens OBS, demonstrating a fundamental tension between internal and output-level fairness that existing frameworks are unequipped to diagnose.
Abstract (translated)
URL
https://arxiv.org/abs/2608.08284
PDF
-
HugSelect: An Explainable Multi-Criteria Decision-Support Framework for foundation-model selection
2026-08-08 11:28:10Alireza Joonbakhsh (Shiraz University), Arda Canser Adal{\i} (Utrecht University), Slinger Jansen (Utrecht University), Farshad Khunjush (Shiraz University), Siamak Farshidi (Wageningen University,Research)Abstract
Foundation models are increasingly reused as software components, making model selection a critical software-engineering decision. Current model hubs primarily support discovery through popularity metrics, often neglecting functional capabilities, operational constraints, and community-perceived quality. We argue that foundation-model selection should be treated as an explicit, auditable software-component selection task rather than as keyword search, popularity ranking, or opaque conversational advice. This paper proposes HugSelect, an explainable decision-support framework for foundation-model selection. HugSelect builds a knowledge base of 71,274 models by combining repository metadata, extracted functional capabilities, and perceived quality attributes derived from community discussions into a unified pipeline. It ranks candidate models using a weighted additive model that exposes criterion-level score decompositions. We evaluated HugSelect through pipeline validation, comparative case studies against four commercial LLM-based recommendation systems (44 scenarios), fine-grained ablation, and an exploratory user study (n = 10). Extraction pipelines achieved an F1 score of 0.801 for functional features and an accuracy of 0.84 for quality-attribute mapping. HugSelect achieved a model-level Coverage@10 of 0.61 and family-level Coverage@10 of 0.91, showing recommendation quality comparable to that of the evaluated commercial systems, with no significant overall differences in ranking quality, while providing stable, traceable, and inspectable reasoning. Ablation confirmed that functional features were the main driver of retrieval accuracy, and preliminary user feedback suggests that the framework is useful and intuitive.
Abstract (translated)
URL
https://arxiv.org/abs/2608.08069
PDF
-
Beyond 'I Can't Help With That': How Child Safety Experts Evaluate AI Chatbot Safety
2026-08-08 04:00:10Hannah Cha, Neha Shukla, Solon Barocas, Alexandra Chouldechova, Eugenia Kim, Jennifer Wortman VaughanAbstract
Youth increasingly turn to AI chatbots for social and emotional support, raising concerns about how these systems respond, especially in high-stakes situations. However, existing child safety evaluations of AI lack grounding in real-world harms that youth experience, rely on unvalidated assumptions about what counts as an appropriate output (e.g., refusal), and typically focus on detecting adversarial prompts or surface-level harms in outputs only. Thus, these evaluations can fail to detect responses that pose harm to youth in practice. To better understand the limitations of current evaluation practices, we conducted interviews with 19 practitioners working directly with youth in vulnerable situations, including social workers, therapists, and psychologists, asking them to reflect on chatbots' responses to risky situations commonly faced by youth, as established in prior empirical work. Practitioners identified chatbot behaviors likely to cause harm as well as those that could meaningfully support youth in difficult moments, discussed the role that chatbots should (and should not) play in these interactions, and offered concrete recommendations for improving chatbot responses. Based on these findings, we provide recommendations for AI child safety evaluation and infrastructure, and highlight the need for incorporating practitioners' perspectives into safety work.
Abstract (translated)
URL
https://arxiv.org/abs/2608.07902
PDF
-
Do LLM Recommenders Know When They're Hallucinating? Auditing Confidence Calibration in Catalog Faithfulness
2026-08-07 21:41:16Srijith RavikumarAbstract
LLM recommenders for top-$K$ item suggestion regularly emit titles outside the target catalog. Prior audits measure this as a binary out-of-domain rate; none ask whether the model knew it was hallucinating. We jointly audit hallucination rate (OOD@10) and verbalized-confidence calibration (ECE, Brier, reliability) for four zero-shot LLM recommenders from four independent vendors (Mistral Large, Llama-3.3-70B, GPT-OSS-120B, Claude Sonnet 4.6), not grounded or fine-tuned systems, across three catalogs (MovieLens-25M, Amazon Reviews 2023 Toys, Yelp Open Dataset), stratified by item popularity. Hallucination is catalog-dependent (0--0.2\% on MovieLens, 4.5--8.3\% on Amazon, 2.2--8.4\% on Yelp), but verbalized confidence is materially miscalibrated even when hallucination is zero (ECE up to 0.223 on MovieLens despite 0\% OOD). All four LLMs are systematically \emph{under}-confident across all twelve cells, verbalizing a mean of 67--86 on items they recommend with 92--100\% accuracy. This is the opposite of the over-confidence usually emphasized in LLM-hallucination work. The under-confidence is best read as an \emph{elicitation mismatch}: ``Just Ask'' elicits a generic recommendation-quality rating, not a catalog-membership probability. A conformal abstention threshold over verbalized confidence reduces hallucination by at most 0.7\,pp across $\alpha \in \{.05, .10, .15, .20\}$, at 4--21\,pp of coverage cost: the under-confident channel cannot separate correct items from hallucinations, so the threshold mostly removes correct items. We recommend that audits of LLM recommenders report calibration alongside OOD, and use catalog-anchored elicitation rather than generic confidence prompts.
Abstract (translated)
URL
https://arxiv.org/abs/2608.10008
PDF
-
LGNNIC: Acceleration of Large-Scale GNN Training using SmartNICs
2026-08-07 19:55:45Liad Gerstman, Aditya Dhakal, Dejan Milojicic, Avi MendelsonAbstract
Graph Neural Networks (GNNs) are widely used across domains such as natural sciences, social network analysis, chip design, and recommendation systems. However, as graph sizes grow, storing and processing them entirely on a single-node CPU-GPU system becomes increasingly impractical. A promising approach is to distribute the graph across multiple remote memory nodes, though this introduces a major bottleneck: inter-node network congestion during training. To address this, we propose LGNNIC, a novel inter-node system architecture that leverages SmartNICs co-located with remote memory nodes-a configuration already available in modern systems-to reduce communication overhead in distributed GNN training. LGNNIC offloads key preprocessing tasks to SmartNICs, reducing the volume of data transferred to computational (training) nodes and alleviating network congestion. We introduce two complementary techniques executed on the SmartNICs during the preprocessing phase: Neighbor Sampling, which performs mini-batch sampling, and Quantization of the sampled batches. To evaluate LGNNIC under different communication infrastructures, we designed both an optimized low-overhead DMA-based synchronization mechanism and a high-overhead socket-based alternative used as a benchmark. We evaluate the core SmartNIC offloading mechanisms across standard GNN workloads and sampling hyperparameters using a proof-of-concept (PoC) system comprising one remote-memory node with an NVIDIA BlueField-2 SmartNIC and one compute node with an A100 GPU. Both Neighbor Sampling and Quantization on the remote node demonstrated substantial training speedups in most configurations. Neighbor Sampling achieved up to 62.4x and 17.5x speedups with Sockets and DOCA-DMA, respectively, primarily due to reduced data transaction time. Quantization provided additional speedups of up to 3.6x and 1.3x, respectively, by reducing data transfer.
Abstract (translated)
URL
https://arxiv.org/abs/2608.07733
PDF
-
IntelliAudit: Using Large Language Models to Evaluate Audit Controls
2026-08-07 18:21:06Allison Wilson, Sina Moradi Sabet, Diar Shakimov, Panteha Shahrivar, Mohammad Reza Bagheri, Dean Konenkamp, Mohammad A. TayebiAbstract
IT audits require auditors to judge whether heterogeneous organizational evidence satisfies semantic security and compliance controls. This judgment is difficult to automate because relevant evidence is distributed across policies, records, spreadsheets, and operational artifacts, and because audit conclusions depend on evidentiary sufficiency rather than keyword matching. We present IntelliAudit, a retrieval-grounded multi-agent system for IT audit evidence evaluation. Given a control and an evidence corpus, IntelliAudit retrieves relevant artifacts, generates an evidence-grounded assessment, challenges adverse findings, adjudicates disagreements, and produces an auditor-facing recommendation with cited evidence, rationale, missing-evidence analysis, and remediation guidance. We instantiate IntelliAudit on ISO/IEC 27001 and evaluate it across multiple simulated organizations using expert auditor review and audit-readiness user feedback. The evaluation shows that IntelliAudit can support control interpretation, evidence-grounded reasoning, and audit-preparation workflows, while also revealing the importance of human oversight for calibrating sufficiency judgments and correcting overly permissive recommendations. These results suggest that retrieval-grounded multi-agent systems can assist audit evidence review, but should remain decision-support tools rather than autonomous certification systems.
Abstract (translated)
URL
https://arxiv.org/abs/2608.07688
PDF
-
The Utility of LLMs in Recommender Systems Explanation Evaluation
2026-08-07 08:49:13Kathrin Wardatzky, Oana Inel, Luca Rossetto, Abraham BernsteinAbstract
Explanations play a crucial role in creating trustworthy recommender systems (RS), yet choosing a good explanation method presents challenges. Many explanation methods exist, but little guidance exists on which is best for which setting. Existing explanation generation methods often produce abstract outputs that require further formatting to become user-friendly, with a seemingly endless pool of options. Running user-based evaluations of all possible options is usually unfeasible, while automated evaluation metrics often either assess only the explainer's abstract output or require comparison with a ground truth, which is generally unavailable. Recent studies have shown that large language models (LLMs) can serve as ``judges'' for explanation evaluation, but their reliability has not yet been thoroughly explored. This paper studies the utility of LLMs in selecting an effective explanation method for a given application. We first explore their ability to generate explanation prototypes given varying information about the RS and the user. Specifically, we generate 18 distinct explanation prototypes, which are subsequently evaluated by 14 LLMs of varying sizes across two temperature settings. We compare these against human ratings derived from a user study. Our results show that while LLMs exhibit human-like rating patterns and achieve moderate rank correlation with human raters, their absolute rating agreement is low and varies substantially by model size and evaluation construct. We derive four practical recommendations: keep explanation-generation prompts concise, prefer larger models for evaluation, pre-test evaluation constructs, and audit explanations for factual accuracy, as neither humans nor LLMs reliably detect non-factual content.
Abstract (translated)
URL
https://arxiv.org/abs/2609.01627
PDF
-
Critical Acclaim Orientation in Large Language Models: Evidence from Film Preference Elicitation
Abstract
Large language models (LLMs) are trained on corpora that contain expressions of human judgment about films, books, music, and more. Yet whether LLMs systematically reproduce evaluative hierarchies remains unclear. Prior research on cultural bias in LLMs suggests competing expectations: models may mirror the popularity signals of internet texts, or may reproduce forms of prestige embedded in critical discourse. We probe this question through a study of film evaluations with eight models from four families (Anthropic, OpenAI, Alibaba, and Mistral), using a 200-film benchmark partitioned into critically acclaimed, commercially successful, and dual-legitimacy (critical acclaim + commercial success) films. Across 20,000 pairwise forced-choice comparisons per model analyzed with Bradley--Terry estimation, we observe a consistent critical acclaim orientation with all models: critically acclaimed yet commercially obscure films are selected over commercially successful yet critically unrecognized ones. This pattern grows with model scale within each family. In addition, nested OLS regression analyses show that evaluative orientation, public visibility, and popular reception distinctly help explain preferences. Adjusting for public visibility reverses the models' preference for dual-legitimacy films over critical acclaim-only films, while additionally accounting for popular reception attenuates much of the disadvantage of films with commercial success only. Finally, evaluative and recommendation-oriented prompt framings produce divergent rankings, suggesting that critical acclaim orientation may manifest indirectly in real-world LLM deployments.
Abstract (translated)
URL
https://arxiv.org/abs/2608.06955
PDF
-
Progressive Alignment of Recommender Foundation Model through Multi-Phase Post-Training
2026-08-07 04:30:34Oseong Choi, Hoeinn Kim, Jihoon Lee, Byungsoo Kang, Taeyeong JangAbstract
Foundation model(FM) for recommendation has shown strong ability to model long-horizon sequential user behavior. In practice, a single pretrained foundation model is often adapted to diverse downstream serving surfaces through Supervised Fine-Tuning(SFT). However, optimizing task-specific objectives such as clicks or likes does not necessarily align the serving policy with the business metrics that determine recommendation quality. We propose a three-phase progressive post-training framework that explicitly separates downstream adaptation from business-metric alignment. The adaptation stage is decomposed into Linear Probing(LP) and Full Fine-Tuning(FFT): LP first stabilizes randomly initialized downstream heads within a frozen pretrained representation space, and FFT then jointly specializes the full model for the target task. On top of this stabilized policy, Reinforcement Fine-Tuning(RFT) aligns the model with practical business objectives using a learned reward model. Rather than directly optimizing the serving policy on sparse business targets, we train the policy on dense implicit feedback and use business-metric supervision only for reward modeling. Offline experiments show that the progressive LP-FFT-RFT framework outperforms single-phase alternatives, and that reward-based alignment yields a stronger serving policy than directly using the reward model itself for ranking. Large-scale online A/B tests further show that the proposed framework improves production recommendation quality over a conventional non-foundation baseline. A reference implementation is available at this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2608.06792
PDF
-
Shape Your Feed: An LLM-based Agentic System for Conversational Recommendation
2026-08-06 22:54:16Ziyun Xu, Bosen Ding, Yue Zhang, Ji Qi, Qingyuan Song, Jizhou Huang, Liwei Wang, Jefferey Santelli, Yue Weng, Qichao Que, Zhenheng Yang, Junfeng Pan, Linhong ZhuAbstract
Industrial recommendation systems predominantly adopt a passive ranking paradigm that infers user preferences from implicit behavioral signals (e.g., clicks, dwell time) rather than explicit, natural language inputs. As a result, users experience a persistent discrepancy between their explicit interests and what passive behavioral algorithms deliver, limiting their ability to express nuanced preferences or steer their feed in real time. To address this growing gap between how recommendations are optimized and how users wish to articulate their interests, we present Shape Your Feed (SYF), an LLM-based agentic recommendation framework that enables real-time, multimodal co-curation of content. SYF employs a three-tier architecture: (i) a Perception Flow that captures fine-grained user intent from text prompts, voice commands, and UI interactions; (ii) a Serving Flow that performs real-time agentic re-ranking and pruning of candidate items, grounded in a persistent Semantic Profile encoding evolving user preferences; and (iii) a Self-Evolution Flow that aligns system behavior with human judgments via Direct Preference Optimization (DPO) and an LLM-as-a-Judge ensemble. Offline evaluations show that SYF's alignment scoring module achieves 98.85% accuracy, substantially improving over strong few-shot baselines. Large-scale online A/B experiments on production traffic further demonstrate that SYF improves feed relevance and user sentiment, indicating a practical and scalable path toward interactive, user-steerable recommendation in industrial settings.
Abstract (translated)
URL
https://arxiv.org/abs/2608.06632
PDF
-
Agentic AI: User Empowerment or Enclosure?
2026-08-06 18:49:13David Gamba, Daniel M. Romero, Grant SchoenebeckAbstract
Agentic AI promises a more flexible form of digital agency: systems that can act on users' behalf, from filtering content to negotiating prices to selecting services. Whether it will empower users is an open question, and we argue that the answer depends on more than the technology. We conduct a comparative case analysis of four more mature domains where similar forms of agency arose: browser-based ad blockers, platform recommender systems, financial robo-advisors, and email spam governance. Across the cases, decisions about whose interests agents would serve were resolved through technical arrangements: API choices, protocol governance, industry standards, and default configurations. Beyond their technical form, these were political decisions. We identify this as depoliticization, a concept from political theory, here at work in technological systems. Its most consequential effect is that individual outcomes and collective contestation capacity can move in opposite directions: spam inbox quality improved substantially while the organized capacity to contest spam governance collapsed. Where intermediary institutions sustained adversarial challenge, user-aligned agency proved more durable; where proprietary infrastructure and closed standard-setting absorbed contestation, displacement compounded. We apply this to agentic AI, where governance arrangements consolidating around the Model Context Protocol and the Agentic AI Foundation are settling these configurations before the choices that define what agents can do move outside the reach of users and the public.
Abstract (translated)
URL
https://arxiv.org/abs/2608.06510
PDF
