Dialog
-
Leveraging Fine-grained Error Correction in Korean Speech Recognition for Consultation Services
2026-09-09 08:45:20Yonghyun Jun, Jimin Lee, Hwan Chang, Dongho Shin, Seolah Kim, Hwanhee LeeAbstract
Automatic Speech Recognition (ASR) technology is fundamental to customer service automation and large-scale transcription. However, even advanced ASR models exhibit inevitable errors in complex real-world environments such as call center conversations. When privacy restrictions preclude audio access, error correction must rely on text-based post-editing. Existing text-only approaches face significant challenges in low-resource languages, mainly due to a critical scarcity of annotated corpora and tailored correction methodologies. For Korean, this resource gap is particularly pronounced, as existing resources are predominantly designed for ASR training rather than text-based error correction. To address this, we introduce DasanCallDial, the first large-scale Korean benchmark dataset specifically curated for dialogue-level ASR error correction. Derived from genuine call center interactions, it comprises 1,974 dialogues with 115,460 utterances. Leveraging this resource, we propose Detector-Gated Contextual Span Correction (DCSC), a text-only post-editing framework for error-sparse Korean speech recognition transcripts. DCSC combines an encoder-based detector that first performs token-level error detection, followed by a language model-based corrector trained to rectify fine-grained span-level errors. Additionally, we employ dialogue-level context augmentation to enable the model to leverage discourse history for disambiguation. By employing multi-level granularity, our method achieves state-of-the-art performance, effectively overcoming the limitations of general LLMs in low-resource settings.
Abstract (translated)
URL
https://arxiv.org/abs/2609.09889
PDF
-
$S^3$-Bench: Evaluating Speech Interaction Models as Scientific Voice Assistants
2026-09-09 08:06:28Heyang Liu, Jiayi Huang, Wenyang Xiao, Ziyang Cheng, Lixin Zhang, Zhen Liu, Miao He, Ronghua Wu, Qunshan Gu, Yanfeng Wang, Yu WangAbstract
The advance of multimodal large language models (MLLMs) has fundamentally reshaped the paradigm of human-computer interaction, especially speech interaction models capable of seamless conversations. Despite remarkable performance as general voice assistants, their performance in specialized domains remains underexplored, particularly in scientific areas. Scientific interactions introduce formidable challenges, involving rare technical terminology, spoken norms of abbreviations, and the natural verbalization of symbolic special expressions. In this paper, we introduce S$^3$-Bench, a systematic evaluation framework covering 10 major disciplines, consisting of a Knowledge set for speech question-answering and a Dialogue set for multi-turn progressive interactions with simulated user agents. By decomposing a complete atomic turn into stages of speech recognition, perception, knowledge utilization with reasoning, and response pronunciation, we systematically characterize the common challenges and performance tradeoffs of existing approaches. Furthermore, experiments on multi-turn interactions reveal persistent limitations in user adaptation and the generation of accurate, comprehensive, and efficient responses.
Abstract (translated)
URL
https://arxiv.org/abs/2609.09852
PDF
-
SocialRL: Refining LLMs' Social Intelligence through Multi-turn Reinforcement Learning and Reward Design
2026-09-09 06:06:34Jianing Wang, Xintao Wang, Aili Chen, Jie Shi, Hongcheng Guo, Jun Gao, Wenxuan Zhao, Chengkun Lang, Yuanli Guo, Yanghua XiaoAbstract
Social intelligence enables agents to read social context, infer intent, and adapt over sustained dialogue. As language models become autonomous collaborators, it is central to building effective and trustworthy human-AI interaction. Existing reinforcement learning methods optimize single-turn utterances and sparse outcome rewards, producing short-sighted policies that struggle to manage goal-relationship tensions across multi-turn interactions. We propose SocialRL, a multi-turn reinforcement learning framework addressing both challenges. First, we apply multi-turn reinforcement learning using PPO that propagates delayed outcome rewards back to each turn, enabling long-horizon planning. Second, we design six process reward dimensions capturing the goal-relationship trade-off, including goal advancement, relational attunement, contextual coherence, etc. A reward model dynamically generates fine-grained scoring criteria for each dimension, while a stage-aware weight schedule prioritizes relationship-building in early turns, goal advancement mid-way, and balanced closure late. Across multiple social-dialogue benchmarks, SocialRL improves Goal Achievement by an average of 9.2 percentage points over the corresponding Base models. These results demonstrate the effectiveness of SocialRL across synthetic and real social scenes, as well as standard and challenging social scenarios.
Abstract (translated)
URL
https://arxiv.org/abs/2609.09764
PDF
-
X2-NativeCursor: Native-Token Text Progress Tracking for Incremental-Text Streaming Codec TTS
2026-09-09 03:46:14Zehan Liu, Carl Chen, Rime Wen, Kaiqi Fu, Altman Lin, Shawn Qin, Lights Shi, Roy Gan, Hao Wang, Qian WangAbstract
Incremental-text streaming text-to-speech (TTS) needs online text progress tracking for synchronized highlighting, interruption handling, and dialogue-history updates. Input text arrives before it is spoken, so text arrival alone cannot indicate speech progress. Existing waveform-based alignment requires complete audio or adds acoustic processing during streaming. We propose X2-NativeCursor, a lightweight observer that tracks progress from native speech tokens before waveform decoding without changing the TTS generator. Its normalization plan links spoken labels to their original-text spans. Text and native-token encoders feed a local matcher that estimates the current label position. A separate output rule converts revisable position estimates into a cursor that never moves backward. Mean absolute error against an automatic reference is 0.151 Chinese characters with 80-ms lookahead, versus 1.253 characters with 320-ms lookahead for an online waveform baseline. Alignment real-time factor also decreases from 0.3598 to 0.0180 relative to this baseline. Lower tracking error is retained under a second automatic alignment reference. We evaluate X2-NativeCursor on Qwen3-TTS and validate its adaptation to CosyVoice2 by training a separate observer for each backbone. Code is publicly available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.09677
PDF
-
MeClear: Cooperative Game-Theoretic Attribution and Risk-Aware Memory Clearance for Long-Horizon LLM Agents
2026-09-08 17:46:00Boyu Yang, Jiazheng Sun, Zilong Lu, Zhi Qiu, Xin Peng, Jun ZhengAbstract
Long horizon Large Language Model (LLM) agents rely on external memory systems to preserve user preferences and task knowledge across extended interactions. Conventional retrieval mechanisms optimize semantic compatibility rather than downstream utility, frequently introducing outdated, misleading, or conflicting evidence into the active context. We present MeClear, a task conditioned memory clearance framework that identifies memories featuring negative downstream utility through cooperative attribution and selectively suppresses them from agent execution. MeClear combines Leave One Out screening with sampled cooperative Shapley attribution to distribute utility across interacting evidence, effectively resolving redundant conflict masking where single removal evaluations fail. Utilizing attribution rankings, MeClear executes a query scoped minimal clearance strategy over a nested filtration, verifying task recovery on the cleared context without permanently altering the persistent memory bank. Comprehensive experimental evaluations across ten long dialogue memory pools demonstrate that MeClear achieves a target recall of 85.9% and an overall task recovery rate of 82.3%, representing a 25.5 percentage point improvement over Leave One Out (LOO) baselines.
Abstract (translated)
URL
https://arxiv.org/abs/2609.09115
PDF
-
EmoTrack: Clinical-Semantic Modeling for Text-Based Depression Severity Estimation
2026-09-08 13:05:25Zhaomin Wu, Jiayi Li, Bingsheng HeAbstract
Text-based counseling provides a valuable source of information for assessing depression severity. We study prediction of the total score on the eight-item Patient Health Questionnaire (PHQ-8), a self-report measure of depression severity, from counseling transcripts. Clinical-based methods rely mainly on large language model (LLM) inference to obtain structured session-level assessments, but these assessments provide limited information about which utterances support each score. Training-based methods train predictors directly on sentences or their semantic embeddings and preserve local conversational detail, but must learn clinical structure from limited labeled transcripts. Integrating a small set of clinical feature scores with a long sequence of high-dimensional utterance representations is challenging, as simple fusion can overemphasize dialogue evidence and fail to link clinical features to supporting utterances. Combining structured clinical assessments with sentence-level semantics, we propose EmoTrack, which jointly encodes clinical feature scores and utterance representations to predict the total PHQ-8 score. For longitudinal assessment across successive sessions, the model can also incorporate a compressed representation of the preceding session as optional memory. On the real-world DAIC-WOZ benchmark, EmoTrack reduces mean absolute error from 2.8234 to 2.4708 relative to the strongest evaluated baseline. Across five settings covering single-session estimation, cross-dataset transfer without adaptation, and longitudinal assessment, it reduces normalized aggregate error by approximately 6.1% relative to the strongest baseline.
Abstract (translated)
URL
https://arxiv.org/abs/2605.22286
PDF
-
X2Streaming-ASR: wait when uncertain, emit when ready for streaming ASR
2026-09-08 12:39:06Zhiwei Lin, Kaiqi Fu, Rime Wen, Zehan Liu, Shawn Qin, Roy Gan, Hao Wang, Qian WangAbstract
Streaming automatic speech recognition (ASR) for real-time voice agents and full-duplex dialogue must provide accurate partial transcripts with low commit latency. Existing systems commonly use a fixed chunk size, look-ahead, or target delay, or encourage emissions near estimated acoustic boundaries. These approaches do not directly optimize how much additional context to use at each output position under a single-pass, hard-commit constraint. We propose X2Streaming-ASR, which decomposes streaming recognition into when to commit and what to commit. Its three-stage training procedure first establishes streaming recognition ability, then warm-starts the commit policy with automatically probed trajectories, and finally refines the policy using character-level, segment-assigned group-relative rewards for recognition accuracy and latency. Across AISHELL-1/2/3 and WenetSpeech, X2Streaming-ASR achieves a mean character-level commit latency of 27-84 ms relative to forced-aligned character endpoints, compared with 409-585 ms for the evaluated streaming baselines. It achieves the best streaming CER among the evaluated systems on AISHELL-1 and AISHELL-3 with substantially lower latency.
Abstract (translated)
URL
https://arxiv.org/abs/2609.08672
PDF
-
BIO-MEMART: Biometric-Aware KV Cache Memory for Multi-User LLM Agents
2026-09-08 10:56:17Yanhong Qian, Xuanying He, Qingguo Meng, Shihao Ding, Xingbo Dong, Zhe JinAbstract
KV cache is evolving from a serving optimization into an external memory substrate for long-term LLM agents. In a shared multi-user deployment, however, reusable KV blocks introduce a missing access-control question: semantic relevance alone cannot determine whether a memory block is authorized for the current physical user. We propose Bio-MemArt, a biometric-aware KV-cache memory framework for multi-user LLM agents. Bio-MemArt attaches a normalized biometric template to each stored KV memory block, filters the shared memory pool with the current user's biometric probe, and then runs the original MemArt retrieval and KV reuse pipeline only inside the authorized candidate pool. This design preserves latent-space retrieval, direct cache reuse, and decoupled position encoding while adding physical-user access control to shared KV memory. We evaluate Bio-MemArt under Owner and Non-owner query conditions on long-term dialogue QA with face and palmprint benchmarks. Across face benchmarks, the average owner and non-owner biometric success rates are 95.71% and 0.86%; across palmprint benchmarks, they are 97.60% and 2.00%. In the efficiency study, average prefill tokens drop from 18,781.96 under full-context prompting to 28.57 with Bio-MemArt, showing that biometric gating preserves the low-token operating regime of KV-cache memory.
Abstract (translated)
URL
https://arxiv.org/abs/2609.08566
PDF
-
Noise Adaptive Streaming Audio-Visual Speech Token Enhancement for Robust Full-Duplex Spoken Dialogue Models
2026-09-08 07:59:13Bella Godiva, Yeonju Kim, Yong Man RoAbstract
Full-duplex spoken dialogue systems enable simultaneous listening and speaking, but their audio-only perception often fails under background noise and overlapping speech, leading to incoherent responses. Recent audio-visual dialogue approaches show that incorporating visual cues such as lip movements improve robustness under audio corruption. However, existing approaches often adapt the large speech dialogue model itself to process visual input, requiring costly multimodal training. We propose AV-STE, a modular streaming audio-visual front-end that restores corrupted semantic speech tokens from noisy audio and lip video before they reach the speech LLM. The downstream dialogue model remains entirely frozen, preserving its pretrained conversational capabilities. When integrated with frozen Moshi, AV-STE improves average GPT-4o-judged response coherence from 1.42 to 1.91 under same-dataset speaker interference while largely preserving turn-taking behavior. Gains also transfer to out-of-domain Seamless Interaction.
Abstract (translated)
URL
https://arxiv.org/abs/2609.08390
PDF
-
MemForest: Efficient Agent Memory Management via EventTree Partitioning and Progressive Merging
2026-09-08 05:30:30Junxi Wang, Te Sun, Jiayi Zhu, Chen Zhang, Siyuan Li, Xuyang Liu, Zichen Wen, Xiaobing Tu, Jinkui Ren, Xiantao Zhang, Ziqi Yuan, Linfeng ZhangAbstract
Agent memory systems have demonstrated significant potential in long-term dialogue, personalized assistants, and video understanding. However, continuously accumulated memory introduces substantial storage and retrieval costs during inference. To address this issue, we propose \textbf{MemForest}, a general memory compression framework adaptable to various agent memory systems. Specifically, MemForest partitions historical memory into event-centric units by leveraging global semantic similarity and local temporal continuity. For each unit, it constructs a maximum spanning tree, termed an EventTree, and progressively merges redundant memory nodes by selecting high-weight edges, reducing storage overhead. Furthermore, we introduce an anchor-guided propagation retrieval mechanism that retrieves relevant memory nodes from the temporal neighborhoods of key nodes, improving retrieval accuracy. Extensive experiments demonstrate the effectiveness of MemForest. Under the unimodal Mem0 framework, MemForest retains \textbf{97.1%} of the original performance while compressing \textbf{50%} of historical memory across three benchmarks (LoCoMo, LongMemEval, and PersonaMem), achieving a \textbf{1.89x} retrieval speedup. Under the multimodal M3-Agent framework, it preserves \textbf{99.7%} of the original performance with a \textbf{50%} compression ratio across two benchmarks (M3-Bench-robot and M3-Bench-web), achieving a \textbf{2.24x} retrieval speedup. \textcolor{RoyalBlue}{\textit{Our code is available at [this https URL.}}](this https URL.}})
Abstract (translated)
URL
https://arxiv.org/abs/2609.08273
PDF
-
Large-Scale User Behavior Analysis in Multimodal AI-Assisted Manual Task Execution
2026-09-07 15:06:21Rafael Ferreira, Diogo Tavares, Diogo Gl\'oria-Silva, David Semedo, Jo\~ao Magalh\~aesAbstract
Conversational Task Assistants (CTAs) are multimodal dialogue systems that support users in complex real-world tasks such as cooking and DIY through voice, text, image, and video interactions. Prior user studies have focused on controlled settings, leaving limited understanding of real-world CTA usage at scale. In this work, we present a large-scale study of CTA usage based on thousands of users in-the-wild. Our large-scale real-world data analysis unveils new understandings of (i) user-CTA interaction flows, (ii) user intents, (iii) user conversational traits, and (iv) behavioral factors associated with user satisfaction. Our findings reveal key opportunities for future research in CTAs, particularly in user interaction design and task engagement, concluding with concrete design guidelines.
Abstract (translated)
URL
https://arxiv.org/abs/2609.07594
PDF
-
Encoded Early, Used Late: Where Transformers Begin to Act on an Inferred Partner's Expertise
Abstract
A transformer can make an attribute linearly decodable in its residual stream at a depth where that attribute does not yet influence the output. This gap between where information is readable and where it is used has been shown for attributes stated directly in the input. We ask whether it also holds for an attribute the model must infer gradually over a conversation, namely how expert its dialogue partner is. Using ExpertCollab, a corpus of multi-turn research-planning dialogues between model-played personas at four expertise levels, we find that partner expertise is most decodable in the early layers and falls to near chance before the midpoint of the network. Counterfactual patching shows that injecting the expertise difference at the layer of peak decodability barely changes a fixed late-layer readout, whereas the same difference injected past the midpoint propagates almost completely, a separation of more than an order of magnitude. A content-matched random control and a probe-free diagnostic place the transition at the same early layer, and a statically specified control attribute stays decodable throughout. An inferred relational attribute is therefore represented well before it becomes causally active, which bounds where any attempt to read out or steer partner-conditioned behavior must intervene. We use one model on a synthetic corpus as an initial demonstration.
Abstract (translated)
URL
https://arxiv.org/abs/2609.07139
PDF
-
DIPLOMAT: Dialogue-Span-Aware Direct Preference Optimization for Polite Persuasive Workplace Negotiation Dialogues
2026-09-06 09:14:39Bibhuti Jha, Rishikant Chigrupaatii, Priyanshu Priya, Asif EkbalAbstract
Effective workplace negotiation requires balancing multiple objectives, including achieving task goals, preserving professional relationships, and resolving conflicts constructively. However, misunderstandings, misaligned preferences, and interpersonal friction often impede successful outcomes. Politeness mitigates these challenges by fostering trust, reducing tension, and preventing escalation, and persuasive communication helps overcome resistance, align preferences, and guide participants toward mutually beneficial agreements. Motivated by these insights, we present DIPLOMAT, a dialogue system for polite and persuasive workplace negotiation. To support its development, we introduce PROWESS, a dataset of multi-turn workplace negotiation dialogues generated via a multi-agent framework and enriched withnegotiation strategies, politeness levels, persuasive strategies. DIPLOMAT is trained using Dialogue-Span-Aware Direct Preference Optimization (DSA-DPO), a novel preference learning objective that identifies key dialogue spans for preference alignment. This enables DIPLOMAT to generate contextually coherent responses that employ intended negotiation strategies, maintain politeness, and incorporate effective persuasion strategies throughout interactions. Automatic and human evaluation on PROWESS confirm that DIPLOMAT consistently outperforms baselines in generating coherent, polite, and persuasive negotiation responses.
Abstract (translated)
URL
https://arxiv.org/abs/2609.22256
PDF
-
Deep Persona: A Psychologically Grounded Architecture and Evaluation Framework for Role-Playing Agents and Simulations
2026-09-06 08:53:41Rotem Dror, Zohar Elyoseph, Yuval Haber, Elad Refoua, Oshrat Ayalon, Adir SolomonAbstract
Existing approaches to persona simulation with Large Language Models (LLMs) mostly rely on shallow character descriptions that fail to sustain coherent character behavior across extended interactions. We introduce Deep Persona, a psychologically grounded, three-layered architecture that organizes personas into hierarchical levels of observable expression, latent beliefs, and core motivational drives, for constructing highly convincing role-playing agents. Governed by the principles of scripted determinism and bounded agency, the architecture restricts the model to a reactive engine guided by a structured internal script. We further propose a reference-free evaluation framework that benchmarks dialogue naturalness against empirical human distributions using established psychological clinical instruments and adversarial stress-tests. Empirical evaluation reveals that while LLMs achieve high pragmatic fluency, they exhibit systematic limitations in emotional expression and joint attention. In addition, we present a case study of two Deep Personas and evaluate them using the proposed framework, demonstrating that structured personas can produce interactions that more closely align with human conversational behavior.
Abstract (translated)
URL
https://arxiv.org/abs/2609.22255
PDF
-
Exposing Weaknesses in Emotion Recognition in Conversations
2026-09-05 01:40:01Amir Ben Khalifa, Fanny Bezancon, Amine Trabelsi, Bessam AbdulrazakAbstract
Emotion Recognition in Conversations (ERC) aims to identify speakers' emotions in multi-turn dialogue. Accurate emotion recognition can support a wide range of applications, including empathetic conversational agents, mental health support, and educational technologies. While many recent approaches rely on task-specific fine-tuning, such models may exploit dataset-specific cues. A central yet rarely questioned assumption in ERC is that each utterance can be assigned a single unambiguous emotion label. To investigate this assumption, we study ERC using Large Language Models (LLMs) in a zero-shot setting while incorporating preceding conversational turns as context. We show that aggregate metrics mask systematic failures. Errors concentrate around utterances containing negations, exclamations, and interjections. This pattern is consistent across all evaluated models, suggesting limitations in the benchmarks rather than model-specific weaknesses. A controlled re-annotation study involving four human annotators supports this finding: strong agreement is observed in only 35 percent of cases, with neutral utterances dominating high-agreement instances, while many emotional categories fall into low-agreement regimes. These findings suggest that many apparent model errors reflect genuine annotation ambiguity rather than poor emotion understanding. Standard single-label evaluation is therefore insufficient. To address this limitation, we introduce an LLM-as-Judge framework that evaluates each emotion independently according to its plausibility in the conversational context rather than enforcing a single-label decision.
Abstract (translated)
URL
https://arxiv.org/abs/2609.05806
PDF
-
CC-Mediation: Evaluating Large Language Models for Cross-Cultural Conflict Mediation
2026-09-04 08:10:33Suhyun Lee, Wenxuan Zhang, W. Quin Yow, Yang DengAbstract
Cross-cultural mediation by large language models (LLMs) requires deciding both when to intervene and how to respond in culturally grounded conflicts. Progress on this problem has been limited by the lack of (1) mediation datasets with measurable downstream effects and (2) principled metrics for evaluating intercultural stance change. To address these gaps, we introduce CC-Mediation, a cross-cultural mediation benchmark of $1{,}661$ ten-turn dialogues grounded in the Developmental Model of Intercultural Sensitivity (DMIS), containing culturally grounded conflicts, mediation interventions, and post-intervention trajectories. We further propose two DMIS-based evaluation metrics: Trajectory AUC, which measures the persistence of intercultural improvement over time, and a signed Wasserstein-1 distance, which measures the magnitude and direction of shifts in intercultural stance. Both metrics show strong agreement with human judgment of DMIS-grounded stance shift. Using CC-Mediation, we find that current LLMs have limitations on both axes: intervention timing (when) failure stems from a positional prior that ignores dialogue content, while mediation strategy (how) failure arises from a late-layer elicitation collapse rather than a knowledge deficit.
Abstract (translated)
URL
https://arxiv.org/abs/2609.04855
PDF
-
Controlling and Assessing Appropriate Persona Use in LLM-based Dialogue Generation
Abstract
In persona-based dialogue generation (PDG), LLMs often overuse persona attributes by incorporating them regardless of dialogue context, resulting in unnatural responses. Despite its practical significance, the underlying causes remain unexplored, with no method to mitigate this problem or metric to assess the appropriateness of persona use. To address these issues, we first conduct a comprehensive analysis of LLM-based PDG, revealing that LLMs exhibit a systematic bias to incorporate all given persona attributes, and that existing metrics fail to capture contextual appropriateness. Building on these findings, we propose Self-CONtrastive Persona Overuse Suppression (SCONPOS) to mitigate overuse by directly intervening in LLMs' internal representations at the prompt encoding stage, without requiring any response generation. We further propose the Persona Appropriateness Score (PAS), a novel metric that penalizes both overuse and underuse. Experimental results demonstrate that SCONPOS systematically reduces overuse, and PAS captures the contextual appropriateness of persona use.
Abstract (translated)
URL
https://arxiv.org/abs/2609.04676
PDF
-
TRILOGUE: A Trilingual Spoken Dialogue Fact-Checking Benchmark with Evidence and Paired Audio
2026-09-03 20:14:48Chaewan Chun, Meruyert Aristombayeva, Jiyoung Choi, Mahjabin Nahar, Delvin Ce Zhang, Dongwon LeeAbstract
Modern misinformation is often heard before it is read, yet fact-checking systems are still evaluated mainly on clean written claims. Spoken dialogue remains different even when systems operate on transcripts: claims may be distributed across speakers and turns, depend on prior context, and become harder to verify when Automatic Speech Recognition (ASR) errors distort the available text. Prior spoken dialogue fact-checking resources are small, English-centric, or focused on annotation rather than end-to-end benchmarking, leaving no large multilingual benchmark with paired speech and turn-level labels. We introduce TRILOGUE (TRIlingual spoken diaLOGUE fact-checking), a large-scale trilingual benchmark of source-grounded spoken dialogues in English, Russian, and Kazakh. It contains nearly 12K dialogues, 187K turns, and 390 hours of paired audio with ASR transcripts and word-level timestamp alignments across all three languages, including nearly 5K human-recorded Russian and Kazakh dialogue files. TRILOGUE supports claim check-worthiness detection, source-article evidence retrieval, and claim verification with claim-only, gold-evidence, and retrieved-evidence inputs. Baselines show that ASR degradation and cross-lingual transfer remain challenging, especially for Kazakh, while retrieved source evidence substantially narrows the gap to gold-evidence verification.
Abstract (translated)
URL
https://arxiv.org/abs/2609.04452
PDF
-
Translation as a Decision Space: A Multi-Agent Perspective on Low-Resource Dialect Generation
2026-09-03 16:22:18Hasan Alkhder, Mohammad Abboush, Igor Tchappi, Ahmet Zengin, Amro NajjarAbstract
Neural machine translation (NMT) systems typically produce a single output per input, obscuring the alternative decision trajectories implicitly available within multilingual decoding. This opacity becomes particularly problematic in low-resource dialect settings, where multiple linguistically valid realizations may differ in lexical authenticity, register, and structural stability. We propose reframing translation as a structured decision space explored by autonomous translation agents. Instead of analyzing a single output, we model distinct translation pathways as agents operating over a shared multilingual backbone. Inter-agent divergence is treated not as error but as an interpretable behavioral signal. We conduct an empirical study on Turkish--Syrian Arabic translation using three agents: (1) zero-shot direct translation, (2) dialect-stabilized translation via lightweight fine-tuning, and (3) pivot translation through English. Evaluation is performed on 5,000 dialogue sentences, while stabilization is trained on 5,000 additional Turkish--Syrian sentence pairs drawn from television dialogue and MADAR-Turk resources. Rather than optimizing for conventional performance metrics, we quantify structured behavioral displacement using dialect marker frequency, lexical proximity to standardized Arabic, and structural variance. Lightweight stabilization nearly doubles dialect marker usage, increasing it from 0.2266 to 0.4988, while significantly reducing structural instability. Pivot mediation introduces normalization pressure and measurable compression effects, whereas zero-shot translation exhibits the highest decision variance. We argue that translation divergence across agents reveals latent decision flexibility within multilingual models and we provide a principled interpretability framework for low-resource dialect generation.
Abstract (translated)
URL
https://arxiv.org/abs/2609.04048
PDF
-
IRWOZ 2.0: A Large Language Model-driven Dialogue Dataset for Industrial Robot Conversations
2026-09-03 16:08:57Chen Li, Dimitrios ChrysostomouAbstract
IRWOZ has improved industrial human-robot interaction (HRI) dialogue systems through domain-specific annotations. However, its initial version contains substantial noise in dialogue states and utterances, limiting state-tracking accuracy. We introduce IRWOZ 2.0, which addresses these limitations through large language model (LLM) enhanced generation (Mistral/Claude-3.5) and quality refinements. Our improved dataset expands to 390 dialogues across 4 industrial domains (Assembly, Delivery, Position, Relocation), featuring manual corrections and automated typo removal. Benchmark experiments on dialogue state tracking demonstrate significant improvements, with GPT-2's BLEU-4 score increasing from 0.1651 to 0.5604 compared to original IRWOZ. To support industrial HRI research, we publicly released IRWOZ 2.0 dataset at this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2609.04030
PDF
