Summarization
-
HalluClean: A Unified Framework to Combat Hallucinations in LLMs
2025-11-12 02:50:56Yaxin Zhao, Yu ZhangAbstract
Large language models (LLMs) have achieved impressive performance across a wide range of natural language processing tasks, yet they often produce hallucinated content that undermines factual reliability. To address this challenge, we introduce HalluClean, a lightweight and task-agnostic framework for detecting and correcting hallucinations in LLM-generated text. HalluClean adopts a reasoning-enhanced paradigm, explicitly decomposing the process into planning, execution, and revision stages to identify and refine unsupported claims. It employs minimal task-routing prompts to enable zero-shot generalization across diverse domains, without relying on external knowledge sources or supervised detectors. We conduct extensive evaluations on five representative tasks-question answering, dialogue, summarization, math word problems, and contradiction detection. Experimental results show that HalluClean significantly improves factual consistency and outperforms competitive baselines, demonstrating its potential to enhance the trustworthiness of LLM outputs in real-world applications.
Abstract (translated)
URL
https://arxiv.org/abs/2511.08916
PDF
-
Stress Testing Factual Consistency Metrics for Long-Document Summarization
2025-11-10 23:24:25Zain Muhammad Mujahid, Dustin Wright, Isabelle AugensteinAbstract
Evaluating the factual consistency of abstractive text summarization remains a significant challenge, particularly for long documents, where conventional metrics struggle with input length limitations and long-range dependencies. In this work, we systematically evaluate the reliability of six widely used reference-free factuality metrics, originally proposed for short-form summarization, in the long-document setting. We probe metric robustness through seven factuality-preserving perturbations applied to summaries, namely paraphrasing, simplification, synonym replacement, logically equivalent negations, vocabulary reduction, compression, and source text insertion, and further analyze their sensitivity to retrieval context and claim information density. Across three long-form benchmark datasets spanning science fiction, legal, and scientific domains, our results reveal that existing short-form metrics produce inconsistent scores for semantically equivalent summaries and exhibit declining reliability for information-dense claims whose content is semantically similar to many parts of the source document. While expanding the retrieval context improves stability in some domains, no metric consistently maintains factual alignment under long-context conditions. Finally, our results highlight concrete directions for improving factuality evaluation, including multi-span reasoning, context-aware calibration, and training on meaning-preserving variations to enhance robustness in long-form summarization. We release all code, perturbed data, and scripts required to reproduce our results at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2511.07689
PDF
-
StreamKV: Streaming Video Question-Answering with Segment-based KV Cache Retrieval and Compression
2025-11-10 16:25:03Yilong Chen, Xiang Bai, Zhibin Wang, Chengyu Bai, Yuhan Dai, Ming Lu, Shanghang ZhangAbstract
Video Large Language Models (Video-LLMs) have demonstrated significant potential in the areas of video captioning, search, and summarization. However, current Video-LLMs still face challenges with long real-world videos. Recent methods have introduced a retrieval mechanism that retrieves query-relevant KV caches for question answering, enhancing the efficiency and accuracy of long real-world videos. However, the compression and retrieval of KV caches are still not fully explored. In this paper, we propose \textbf{StreamKV}, a training-free framework that seamlessly equips Video-LLMs with advanced KV cache retrieval and compression. Compared to previous methods that used uniform partitioning, StreamKV dynamically partitions video streams into semantic segments, which better preserves semantic information. For KV cache retrieval, StreamKV calculates a summary vector for each segment to retain segment-level information essential for retrieval. For KV cache compression, StreamKV introduces a guidance prompt designed to capture the key semantic elements within each segment, ensuring only the most informative KV caches are retained for answering questions. Moreover, StreamKV unifies KV cache retrieval and compression within a single module, performing both in a layer-adaptive manner, thereby further improving the effectiveness of streaming video question answering. Extensive experiments on public StreamingVQA benchmarks demonstrate that StreamKV significantly outperforms existing Online Video-LLMs, achieving superior accuracy while substantially improving both memory efficiency and computational latency. The code has been released at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2511.07278
PDF
-
Inclusion of Role into Named Entity Recognition and Ranking
2025-11-10 09:39:00Neelesh Kumar Shukla, Sanasam Ranbir SinghAbstract
Most of the Natural Language Processing sys- tems are involved in entity-based processing for several tasks like Information Extraction, Question-Answering, Text-Summarization and so on. A new challenge comes when entities play roles according to their act or attributes in certain context. Entity Role Detection is the task of assigning such roles to the entities. Usu- ally real-world entities are of types: person, lo- cation and organization etc. Roles could be con- sidered as domain-dependent subtypes of these types. In the cases, where retrieving a subset of entities based on their roles is needed, poses the problem of defining the role and entities having those roles. This paper presents the study of study of solving Entity Role Detection prob- lem by modeling it as Named Entity Recogni- tion (NER) and Entity Retrieval/Ranking task. In NER, these roles could be considered as mutually exclusive classes and standard NER methods like sequence tagging could be used. For Entity Retrieval, Roles could be formulated as Query and entities as Collection on which the query needs to be executed. The aspect of Entity Retrieval task, which is different than document retrieval task is that the entities and roles against which they need to be retrieved are indirectly described. We have formulated au- tomated ways of learning representative words and phrases and building representations of roles and entities using them. We have also explored different contexts like sentence and document. Since the roles depend upon con- text, so it is not always possible to have large domain-specific dataset or knowledge bases for learning purposes, so we have tried to exploit the information from small dataset in domain- agnostic way.
Abstract (translated)
URL
https://arxiv.org/abs/2511.06886
PDF
-
NOAH: Benchmarking Narrative Prior driven Hallucination and Omission in Video Large Language Models
2025-11-09 17:41:11Kyuho Lee, Euntae Kim, Jinwoo Choi, Buru ChangAbstract
Video large language models (Video LLMs) have recently achieved strong performance on tasks such as captioning, summarization, and question answering. Many models and training methods explicitly encourage continuity across events to enhance narrative coherence. While this improves fluency, it also introduces an inductive bias that prioritizes storyline consistency over strict grounding in visual evidence. We identify this bias, which we call narrative prior, as a key driver of two errors: hallucinations, where non-existent events are introduced or existing ones are misinterpreted, and omissions, where factual events are suppressed because they are misaligned with surrounding context. To systematically evaluate narrative prior-induced errors, we introduce NOAH, a large-scale benchmark that constructs composite videos by inserting clips from other sources into target videos. By varying semantic similarity and insertion position, our benchmark enables controlled and scalable analysis of narrative priors. We design one captioning task with tailored metrics and three QA tasks - Existence, Temporal, and Narrative - yielding more than 60K evaluation samples. Extensive experiments yield three key findings: (i) most Video LLMs exhibit hallucinations and omissions driven by narrative priors, (ii) the patterns of these errors vary across architectures and depend on event similarity and insertion position, and (iii) reliance on narrative priors intensifies under sampling with fewer frames, amplifying errors when event continuity is weak. We establish NOAH as the first standardized evaluation of narrative prior-induced hallucination and omission in Video LLMs, providing a foundation for developing more reliable and trustworthy models. Our benchmark and code are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2511.06475
PDF
-
Assertion-Aware Test Code Summarization with Large Language Models
2025-11-09 04:58:32Anamul Haque Mollah, Ahmed Aljohani, Hyunsook DoAbstract
Unit tests often lack concise summaries that convey test intent, especially in auto-generated or poorly documented codebases. Large Language Models (LLMs) offer a promising solution, but their effectiveness depends heavily on how they are prompted. Unlike generic code summarization, test-code summarization poses distinct challenges because test methods validate expected behavior through assertions rather than im- plementing functionality. This paper presents a new benchmark of 91 real-world Java test cases paired with developer-written summaries and conducts a controlled ablation study to investigate how test code-related components-such as the method under test (MUT), assertion messages, and assertion semantics-affect the performance of LLM-generated test summaries. We evaluate four code LLMs (Codex, Codestral, DeepSeek, and Qwen-Coder) across seven prompt configurations using n-gram metrics (BLEU, ROUGE-L, METEOR), semantic similarity (BERTScore), and LLM-based evaluation. Results show that prompting with as- sertion semantics improves summary quality by an average of 0.10 points (2.3%) over full MUT context (4.45 vs. 4.35) while requiring fewer input tokens. Codex and Qwen-Coder achieve the highest alignment with human-written summaries, while DeepSeek underperforms despite high lexical overlap. The replication package is publicly available at this https URL. 5281/zenodo.17067550
Abstract (translated)
URL
https://arxiv.org/abs/2511.06227
PDF
-
BookAsSumQA: An Evaluation Framework for Aspect-Based Book Summarization via Question Answering
2025-11-09 01:54:53Ryuhei Miyazato, Ting-Ruen Wei, Xuyang Wu, Hsin-Tai Wu, Kei HaradaAbstract
Aspect-based summarization aims to generate summaries that highlight specific aspects of a text, enabling more personalized and targeted summaries. However, its application to books remains unexplored due to the difficulty of constructing reference summaries for long text. To address this challenge, we propose BookAsSumQA, a QA-based evaluation framework for aspect-based book summarization. BookAsSumQA automatically generates aspect-specific QA pairs from a narrative knowledge graph to evaluate summary quality based on its question-answering performance. Our experiments using BookAsSumQA revealed that while LLM-based approaches showed higher accuracy on shorter texts, RAG-based methods become more effective as document length increases, making them more efficient and practical for aspect-based book summarization.
Abstract (translated)
URL
https://arxiv.org/abs/2511.06183
PDF
-
Retrieval-Augmented Generation in Medicine: A Scoping Review of Technical Implementations, Clinical Applications, and Ethical Considerations
2025-11-08 07:52:47Rui Yang, Matthew Yu Heng Wong, Huitao Li, Xin Li, Wentao Zhu, Jingchi Liao, Kunyu Yu, Jonathan Chong Kai Liew, Weihao Xuan, Yingjian Chen, Yuhe Ke, Jasmine Chiat Ling Ong, Douglas Teodoro, Chuan Hong, Daniel Shi Wei Ting, Nan LiuAbstract
The rapid growth of medical knowledge and increasing complexity of clinical practice pose challenges. In this context, large language models (LLMs) have demonstrated value; however, inherent limitations remain. Retrieval-augmented generation (RAG) technologies show potential to enhance their clinical applicability. This study reviewed RAG applications in medicine. We found that research primarily relied on publicly available data, with limited application in private data. For retrieval, approaches commonly relied on English-centric embedding models, while LLMs were mostly generic, with limited use of medical-specific LLMs. For evaluation, automated metrics evaluated generation quality and task performance, whereas human evaluation focused on accuracy, completeness, relevance, and fluency, with insufficient attention to bias and safety. RAG applications were concentrated on question answering, report generation, text summarization, and information extraction. Overall, medical RAG remains at an early stage, requiring advances in clinical validation, cross-linguistic adaptation, and support for low-resource settings to enable trustworthy and responsible global use.
Abstract (translated)
URL
https://arxiv.org/abs/2511.05901
PDF
-
CoT-X: An Adaptive Framework for Cross-Model Chain-of-Thought Transfer and Optimization
2025-11-07 22:35:31Ziqian Bi, Kaijie Chen, Tianyang Wang, Junfeng Hao, Xinyuan SongAbstract
Chain-of-Thought (CoT) reasoning enhances the problem-solving ability of large language models (LLMs) but leads to substantial inference overhead, limiting deployment in resource-constrained settings. This paper investigates efficient CoT transfer across models of different scales and architectures through an adaptive reasoning summarization framework. The proposed method compresses reasoning traces via semantic segmentation with importance scoring, budget-aware dynamic compression, and coherence reconstruction, preserving critical reasoning steps while significantly reducing token usage. Experiments on 7{,}501 medical examination questions across 10 specialties show up to 40% higher accuracy than truncation under the same token budgets. Evaluations on 64 model pairs from eight LLMs (1.5B-32B parameters, including DeepSeek-R1 and Qwen3) confirm strong cross-model transferability. Furthermore, a Gaussian Process-based Bayesian optimization module reduces evaluation cost by 84% and reveals a power-law relationship between model size and cross-domain robustness. These results demonstrate that reasoning summarization provides a practical path toward efficient CoT transfer, enabling advanced reasoning under tight computational constraints. Code will be released upon publication.
Abstract (translated)
URL
https://arxiv.org/abs/2511.05747
PDF
-
REFLEX: Reference-Free Evaluation of Log Summarization via Large Language Model Judgment
2025-11-06 23:52:36Priyanka MudgalAbstract
Evaluating log summarization systems is challenging due to the lack of high-quality reference summaries and the limitations of existing metrics like ROUGE and BLEU, which depend on surface-level lexical overlap. We introduce REFLEX, a reference-free evaluation metric for log summarization based on large language model (LLM) judgment. REFLEX uses LLMs as zero-shot evaluators to assess summary quality along dimensions such as relevance, informativeness, and coherence, without requiring gold-standard references or human annotations. We show that REFLEX produces stable, interpretable, and fine-grained evaluations across multiple log summarization dataset, and more effectively distinguishes model outputs than traditional metrics. REFLEX provides a scalable alternative for evaluating log summaries in real-world settings where reference data is scarce or unavailable.
Abstract (translated)
URL
https://arxiv.org/abs/2511.07458
PDF
-
Discourse-Aware Scientific Paper Recommendation via QA-Style Summarization and Multi-Level Contrastive Learning
2025-11-05 09:55:12Shenghua Wang, Zhen YinAbstract
The rapid growth of open-access (OA) publications has intensified the challenge of identifying relevant scientific papers. Due to privacy constraints and limited access to user interaction data, recent efforts have shifted toward content-based recommendation, which relies solely on textual information. However, existing models typically treat papers as unstructured text, neglecting their discourse organization and thereby limiting semantic completeness and interpretability. To address these limitations, we propose OMRC-MR, a hierarchical framework that integrates QA-style OMRC (Objective, Method, Result, Conclusion) summarization, multi-level contrastive learning, and structure-aware re-ranking for scholarly recommendation. The QA-style summarization module converts raw papers into structured and discourse-consistent representations, while multi-level contrastive objectives align semantic representations across metadata, section, and document levels. The final re-ranking stage further refines retrieval precision through contextual similarity calibration. Experiments on DBLP, S2ORC, and the newly constructed Sci-OMRC dataset demonstrate that OMRC-MR consistently surpasses state-of-the-art baselines, achieving up to 7.2% and 3.8% improvements in Precision@10 and Recall@10, respectively. Additional evaluations confirm that QA-style summarization produces more coherent and factually complete representations. Overall, OMRC-MR provides a unified and interpretable content-based paradigm for scientific paper recommendation, advancing trustworthy and privacy-aware scholarly information retrieval.
Abstract (translated)
URL
https://arxiv.org/abs/2511.03330
PDF
-
Beyond Ranked Lists: The SARAL Framework for Cross-Lingual Document Set Retrieval
2025-11-05 06:35:33Shantanu Agarwal, Joel Barry, Elizabeth Boschee, Scott MillerAbstract
Machine Translation for English Retrieval of Information in Any Language (MATERIAL) is an IARPA initiative targeted to advance the state of cross-lingual information retrieval (CLIR). This report provides a detailed description of Information Sciences Institute's (ISI's) Summarization and domain-Adaptive Retrieval Across Language's (SARAL's) effort for MATERIAL. Specifically, we outline our team's novel approach to handle CLIR with emphasis in developing an approach amenable to retrieve a query-relevant document \textit{set}, and not just a ranked document-list. In MATERIAL's Phase-3 evaluations, SARAL exceeded the performance of other teams in five out of six evaluation conditions spanning three different languages (Farsi, Kazakh, and Georgian).
Abstract (translated)
URL
https://arxiv.org/abs/2511.03228
PDF
-
Large language models require a new form of oversight: capability-based monitoring
2025-11-05 01:20:28Katherine C. Kellogg, Bingyang Ye, Yifan Hu, Guergana K. Savova, Byron Wallace, Danielle S. BittermanAbstract
The rapid adoption of large language models (LLMs) in healthcare has been accompanied by scrutiny of their oversight. Existing monitoring approaches, inherited from traditional machine learning (ML), are task-based and founded on assumed performance degradation arising from dataset drift. In contrast, with LLMs, inevitable model degradation due to changes in populations compared to the training dataset cannot be assumed, because LLMs were not trained for any specific task in any given population. We therefore propose a new organizing principle guiding generalist LLM monitoring that is scalable and grounded in how these models are developed and used in practice: capability-based monitoring. Capability-based monitoring is motivated by the fact that LLMs are generalist systems whose overlapping internal capabilities are reused across numerous downstream tasks. Instead of evaluating each downstream task independently, this approach organizes monitoring around shared model capabilities, such as summarization, reasoning, translation, or safety guardrails, in order to enable cross-task detection of systemic weaknesses, long-tail errors, and emergent behaviors that task-based monitoring may miss. We describe considerations for developers, organizational leaders, and professional societies for implementing a capability-based monitoring approach. Ultimately, capability-based monitoring will provide a scalable foundation for safe, adaptive, and collaborative monitoring of LLMs and future generalist artificial intelligence models in healthcare.
Abstract (translated)
URL
https://arxiv.org/abs/2511.03106
PDF
-
Targeted Error Correction in Knowledge Distillation: Small Language Models Surpass GPT
2025-11-04 21:17:49Hee-Jin Lee, Zhen Guo, Luchao Jin, Morteza Moazami GoudarziAbstract
We introduce an Analyze-Revise-Finetune (ARF) pipeline that enables smaller open-source language models (LLMs) to surpass substantially larger proprietary models in customer service summarization tasks. The pipeline first analyzes and categorizes common errors in summaries produced by a teacher model (GPT-3.5), then performs a targeted revision using a compact editor model (Llama 3.1 70B) to generate high-quality, refined training data. Fine-tuning a smaller student model (Llama 3.1 8B) on this refined data resulted in superior summarization performance compared to GPT-3.5. The ARF pipeline improves cost efficiency and data privacy while maintaining competitive accuracy, illustrating a generalizable framework for enhancing open-source LLMs across diverse downstream applications.
Abstract (translated)
URL
https://arxiv.org/abs/2511.03005
PDF
-
Analysis of AdvFusion: Adapter-based Multilingual Learning for Code Large Language Models
2025-11-03 23:45:27Amirreza Esmaeili, Fahd Seddik, Yongyi Ji, Fatemeh Fard, Fuxiang ChenAbstract
Programming languages can benefit from one another by utilizing a language model for software engineering tasks. Full fine-tuning and Parameter Efficient Fine-Tuning (PEFT) of Code Language Models (Code-LMs) has been explored for multilingual knowledge transfer. AdapterFusion is a PEFT architecture that aims to enhance task performance by leveraging information from multiple programming languages, but primarily focuses on the target programming language. In our previous work, we proposed AdvFusion, a novel PEFT-based approach that effectively learns from other programming languages before adapting to the target task. Though previous experiments showed that AdvFusion outperformed AdapterFusion and LoRA, it was applied on pre-trained Code-LMs and was limited to only two tasks, code summarization and method name prediction. In this study, we expanded our work and investigated AdvFusion on Code Large Language Models (Code-LLMs), considering three new tasks: code generation, code translation, and commit message generation. We observed that different Code-LLMs/tasks exhibit different characteristics. In code generation, AdvFusion outperformed AdapterFusion but not other PEFT methods (LoRA, Compacter, and TaskAdapter). In commit message generation, AdapterFusion performed better than AdvFusion, and contrary to code generation, we found that the other PEFT methods do not have better performance. In code translation, AdvFusion performed worse than AdapterFusion overall, with the performance gap marginally widening as the model size increases. However, consistent with code generation, other PEFT methods showed better performance.
Abstract (translated)
URL
https://arxiv.org/abs/2511.02869
PDF
-
Plan-and-Write: Structure-Guided Length Control for LLMs without Model Retraining
2025-11-03 18:10:42Adewale Akinfaderin, Shreyas Subramanian, Akarsha SehwagAbstract
Length control in Large Language Models (LLMs) is a crucial but under-addressed challenge, with applications ranging from voice interfaces requiring concise responses to research summaries needing comprehensive outputs. Current approaches to length control, including Regularized DPO, Length-Instruction Fine Tuning, and tool-augmented methods, typically require expensive model retraining or complex inference-time tooling. This paper presents a prompt engineering methodology that enables precise length control without model retraining. Our structure-guided approach implements deliberate planning and word counting mechanisms within the prompt, encouraging the model to carefully track and adhere to specified length constraints. Comprehensive evaluations across six state-of-the-art LLMs demonstrate that our method significantly improves length fidelity for several models compared to standard prompting when applied to document summarization tasks, particularly for shorter-to-medium length constraints. The proposed technique shows varying benefits across different model architectures, with some models demonstrating up to 37.6% improvement in length adherence. Quality evaluations further reveal that our approach maintains or enhances overall output quality compared to standard prompting techniques. Our approach provides an immediately deployable solution for applications requiring precise length control, particularly valuable for production environments where model retraining is impractical or cost-prohibitive.
Abstract (translated)
URL
https://arxiv.org/abs/2511.01807
PDF
-
SeaLLMs-Audio: Large Audio-Language Models for Southeast Asia
2025-11-03 15:32:58Chaoqun Liu, Mahani Aljunied, Guizhen Chen, Hou Pong Chan, Weiwen Xu, Yu Rong, Wenxuan ZhangAbstract
We introduce SeaLLMs-Audio, the first large audio-language model (LALM) tailored for multiple Southeast Asian (SEA) languages-Indonesian (id), Thai (th), and Vietnamese (vi)-alongside English (en) and Chinese (zh). Trained on a large-scale audio corpus, SeaLLMs-Audio exhibits strong performance across diverse audio-centric tasks, spanning fine-grained audio understanding and voice-based interaction. Its key features include: 1) Multilingual: the model primarily supports 5 languages, namely Indonesian, Thai, Vietnamese, English, and Chinese; 2) Multimodal: the model accepts flexible input modalities, including audio only, text only, as well as audio with text; 3) Multi-task: the model supports a wide range of tasks, including audio analysis tasks such as Audio Captioning, Automatic Speech Recognition, Speech-to-Text Translation, Speech Emotion Recognition, Speech Question Answering, and Speech Summarization. It also enables voice-based dialogue, including answering factual, mathematical, and general knowledge queries. As a significant step towards advancing audio LLMs in Southeast Asia, we expect SeaLLMs-Audio to benefit both the regional research community and industry. To automate LALM evaluation for Southeast Asia, we introduce SeaBench-Audio, a benchmark spanning multiple tasks. Experiments show that SeaLLMs-Audio achieves competitive performance compared with other LALMs on SEA languages.
Abstract (translated)
URL
https://arxiv.org/abs/2511.01670
PDF
-
Prompt Injection as an Emerging Threat: Evaluating the Resilience of Large Language Models
2025-11-03 14:43:56Daniyal Ganiuly, Assel SmaiylAbstract
Large Language Models (LLMs) are increasingly used in intelligent systems that perform reasoning, summarization, and code generation. Their ability to follow natural-language instructions, while powerful, also makes them vulnerable to a new class of attacks known as prompt injection. In these attacks, hidden or malicious instructions are inserted into user inputs or external content, causing the model to ignore its intended task or produce unsafe responses. This study proposes a unified framework for evaluating how resistant Large Language Models (LLMs) are to prompt injection attacks. The framework defines three complementary metrics such as the Resilience Degradation Index (RDI), Safety Compliance Coefficient (SCC), and Instructional Integrity Metric (IIM) to jointly measure robustness, safety, and semantic stability. We evaluated four instruction-tuned models (GPT-4, GPT-4o, LLaMA-3 8B Instruct, and Flan-T5-Large) on five common language tasks: question answering, summarization, translation, reasoning, and code generation. Results show that GPT-4 performs best overall, while open-weight models remain more vulnerable. The findings highlight that strong alignment and safety tuning are more important for resilience than model size alone. Results show that all models remain partially vulnerable, especially to indirect and direct-override attacks. GPT-4 achieved the best overall resilience (RDR = 9.8 %, SCR = 96.4 %), while open-source models exhibited higher performance degradation and lower safety scores. The findings demonstrate that alignment strength and safety tuning play a greater role in resilience than model size alone. The proposed framework offers a structured, reproducible approach for assessing model robustness and provides practical insights for improving LLM safety and reliability.
Abstract (translated)
URL
https://arxiv.org/abs/2511.01634
PDF
-
PrefixNLI: Detecting Factual Inconsistencies as Soon as They Arise
2025-11-03 09:07:44Sapir Harary, Eran Hirsch, Aviv Slobodkin, David Wan, Mohit Bansal, Ido DaganAbstract
Natural Language Inference (NLI) models have been used in various ways to improve the factuality of LLM outputs. This is typically done by applying an NLI model to judge whether the model output is entailed from the supposed evidence, triggering some corrective actions, such as beam reranking at inference time or RL rewards during training. While NLI models are trained to detect factual inconsistencies over complete sentences, decisions in the common autoregressive generation architecture are made for each evolving text prefix, during decoding. Addressing this setting, we generalize the entailment detection task to apply over arbitrary text prefixes, and suggest its utility for improving generation faithfulness. Providing suitable evaluation and training datasets for this task, we train MiniTruePrefixes, a novel specialized model that better detects factual inconsistencies over text prefixes, outperforming comparable baseline NLI models by 5-14 F1 points in prefix-level entailment. We further demonstrate that integrating MiniTruePrefixes into a controlled decoding framework substantially improves factual consistency in abstractive summarization. When guided by MiniTruePrefixes, LLaMA-3.2-3B-Instruct matches the faithfulness and runtime of the 8B model from the same model family, while using only half the memory.
Abstract (translated)
URL
https://arxiv.org/abs/2511.01359
PDF
-
Beyond Permissions: Investigating Mobile Personalization with Simulated Personas
2025-11-03 08:39:38Ibrahim Khalilov, Chaoran Chen, Ziang Xiao, Tianshi Li, Toby Jia-Jun Li, Yaxing YaoAbstract
Mobile applications increasingly rely on sensor data to infer user context and deliver personalized experiences. Yet the mechanisms behind this personalization remain opaque to users and researchers alike. This paper presents a sandbox system that uses sensor spoofing and persona simulation to audit and visualize how mobile apps respond to inferred behaviors. Rather than treating spoofing as adversarial, we demonstrate its use as a tool for behavioral transparency and user empowerment. Our system injects multi-sensor profiles - generated from structured, lifestyle-based personas - into Android devices in real time, enabling users to observe app responses to contexts such as high activity, location shifts, or time-of-day changes. With automated screenshot capture and GPT-4 Vision-based UI summarization, our pipeline helps document subtle personalization cues. Preliminary findings show measurable app adaptations across fitness, e-commerce, and everyday service apps such as weather and navigation. We offer this toolkit as a foundation for privacy-enhancing technologies and user-facing transparency interventions.
Abstract (translated)
URL
https://arxiv.org/abs/2511.01336
PDF
