Latest Dialogue Systems Research Papers

The newest Dialogue Systems papers from across the field — arXiv, NeurIPS, CVPR, Nature, and more — refreshed daily and ranked by relevance. Distill AI tracks Dialogue Systems so you don’t have to: get the standout work delivered to your inbox every morning, with 2-sentence summaries and the option to chat with any paper.

Recent papers

• General and specific aspects of the implementation of the human right to mediation in the legal systems of Italy, Germany, Portugal and Ukraine
  Ruslana Havrylyuk, ПЕТРО ПАЦУРКІВСЬКИЙ · Zenodo (CERN European Organ... · Jan 1, 2027

  This article aims to clarify how the content and guarantees of the right to mediation are formed in modern legal regulation and under what conditions the procedural consequences of initiating the procedure do not destroy the voluntary and s…

• General and specific aspects of the implementation of the human right to mediation in the legal systems of Italy, Germany, Portugal and Ukraine
  Ruslana Havrylyuk, ПЕТРО ПАЦУРКІВСЬКИЙ · Zenodo (CERN European Organ... · Jan 1, 2027

  This article aims to clarify how the content and guarantees of the right to mediation are formed in modern legal regulation and under what conditions the procedural consequences of initiating the procedure do not destroy the voluntary and s…

• Strategic Dialogue Assessment: The Crooked Path to Innocence
  [object Object], [object Object], [object Object] · Dialogue Discourse 2026 · Dec 31, 2026

  Language is often used strategically, particularly in high-stakes, adversarial settings, yet most work on pragmatics and LLMs centers on cooperative settings. This leaves a gap in the systematic understanding of strategic communication in a…

• Homebrewed SLMs: Autoregressive and Masked Diffusion Language Models Built at Home for Portuguese
  Pedro Carvalho Brom · arXiv · Oct 29, 2026

  Building a language model of one's own no longer requires a data centre. This tutorial trains one from scratch, tokenizer included, on one consumer GPU, and shows how to tell whether it is good for the tasks of a specialist domain. It propo…

• Grammar Control for Language Learning with Sequential Monte Carlo and Small Language Models
  Kate McCurdy, Jacob Hoover Vigly, Thomas Hikaru Clark, Karolina Stańczak et al. · arXiv · Oct 29, 2026

  Second language learners benefit from exposure to level-appropriate grammar in interactive language use. While prompted frontier language models can usually produce target grammar structures, less resource-intensive models that can be run o…

• Robustness of Chatbot LLM Judgments of Presidential Actions and Hypothetical Reforms
  Oleg Vasilyev · arXiv · Oct 29, 2026

  Chatbots are increasingly consulted about public affairs, and their judgments of policies are useful only if they are robust. We measure this robustness in the setting of an ordinary user, through consumer chat interfaces. For 30 days, five…

• ETAMem: Decoupling and Aligning Heterogeneous Memory for Long-Term Conversational Agents
  Xinying Qian, Ying Zhang, Yu Zhao, Xubo Liu et al. · arXiv · Oct 27, 2026

  Long-term memory enables Large Language Models (LLMs) to maintain coherent and personalized interactions across extended conversations. However, existing memory systems face two key challenges: (1) Information Entanglement, where heterogene…

• Self-Keyed In-Parameter Memorization for External Memory-Free Dialogue Recall in Frozen Language Models
  XinYu Piao, Myunghoon Ryu, Joongheon Kim, Jong-Kook Kim · arXiv · Oct 27, 2026

  A large language model maintains conversational content in an external storage that is outside the model and grows as the dialogue continues. This work assumes an environment where a language model has no external memory and no prior knowle…

• Words or Deeds? How LLMs Predict Users' Decisions in Human-Agent Dialogue
  Baiqiao Zhang, Shuai Ma, Zhifeng Liao, Chao Zhou et al. · arXiv · Oct 27, 2026

  Web systems increasingly predict users' decisions from what users say, yet when interests partly conflict, users may promise to cooperate to win the other side's cooperation and then not do so. Sales or service agents that rely on such prom…

• Specialization, Diversity, and Scaling in Child-Scale Language Models
  Steven Y. Feng, Michael C. Frank · arXiv · Oct 27, 2026

  Modern language models are trained on far more language than children experience, but we know much less about learning from small, naturalistic datasets. We train small GPT-2 models on transcripts of speech with children from dense home rec…

• Japanese Discourse Structure Analysis Based on Segmented Discourse Representation Theory Using LLMs
  Satomu Tomisaki, Yosuke Mikami, Amane Watahiki, Hitomi Yanaka · arXiv · Oct 27, 2026

  Discourse parsing based on Segmented Discourse Representation Theory (SDRT) is crucial for capturing the structural dynamics of dialogues. However, most prior research focuses on English, and its effectiveness for Japanese remains unclear o…

• Not One Belief: Answer Payloads, Persistence, and Dissociated Confidence Signals in Conversational Question Answering
  Duc-Vinh Tran · arXiv · Oct 26, 2026

  Conversational QA systems should fix errors when users push back and signal which answers to trust. We split each follow-up into its speech act (re-ask, agree, or challenge) and its payload (an answer string, correct or not), and measure fo…

• SimPOTrans: Self-Adaptation for Offline-to-Simultaneous Speech Translation via Reinforcement Learning
  Haotian Tan, Hiroki Ouchi, Sakriani Sakti · arXiv · Oct 26, 2026

  Simultaneous speech translation (SimulST) aims to translate ongoing speech with low latency while preserving translation quality. Recent studies have adopted large language models (LLMs) for SimulST and formulated it as a multi-turn dialogu…

• Synthetic Child-Adult Interactions Are Not Developmentally Plausible
  Bastian Bunzeck, Francesca Padovani · arXiv · Oct 26, 2026

  Synthetic data has become a common resource for training language models, and this trend has spilled over into research on developmentally plausible language modeling. However, it remains unclear whether LM-generated child-adult interaction…

• Diagnosing and Mitigating Long-Session Degradation in Full-Duplex Speech Models
  Junho Kim, CheHyun Lee, Donghun Kang, Youngho Cho et al. · arXiv · Oct 26, 2026

  End-to-end full-duplex spoken dialogue models enable natural, real-time spoken interactions with interruptions, backchannels, and overlapping speech. Prior evaluations have assessed diverse interaction capabilities and identified some degra…

• FATE-5: Faithful Alignment of Trait Expression for Continuous Big Five Personality Control
  Gunhee Cho, Hongyeob Kim, Yun-Gyung Cheong · arXiv · Oct 26, 2026

  Controlling personality in large language models is important for building conversational agents that can be customized to different users and interaction settings. However, existing personality control methods often face a tradeoff between…

• The Language of Instruction: Genre and Generative AI
  James E. Dobson · arXiv · Oct 23, 2026

  This article argues that instruction-fine-tuned language models should be understood as implementing a genre, what is proposed as the instructional-conversational genre. This genre is an amalgamation of discursive language from prior conver…

• Decoupling Patient Personas and Clinical Workflows: A Dual-Agent Approach to Realistic Medical Dialogue Generation
  Qiyuan Li, Xiaomei Guo, Chao Gao, Haijiang Liu et al. · arXiv · Oct 23, 2026

  Pre-consultation medical dialogues are essential for collecting comprehensive patient information, but are costly to obtain at scale due to privacy and ethical constraints. Existing LLM-based synthesis methods often rely on prompt engineeri…

• Profile-Driven User Simulation via Reinforcement Learning with Hierarchical Rewards for Task-Oriented Dialogues
  Juan Li, Fangshu Chang, Xinyi Jiang, Ling Huang et al. · arXiv · Oct 23, 2026

  Building Task-Oriented Dialogue (TOD) systems for high-value scenarios such as financial marketing requires large volumes of domain-specific dialogue data, which privacy regulations, annotation costs, and the need for expert labor make hard…

• Why Full-Duplex Speech Models Collapse in Long Conversations
  Yeonju Kim, Bella Godiva, Se Jin Park, Yong Man Ro · arXiv · Oct 23, 2026

  Full-duplex speech models listen and speak at the same time, which makes them promising for natural, open-ended conversation. But can they sustain a coherent conversation for tens of minutes? Because they generate a token every frame, even …

• CRM-Agent-Bench: Benchmarking Tool-Using Agents in Stateful Enterprise Environments
  Monojit Banerjee, Zhujun Lan, Defu Cao · arXiv · Oct 23, 2026

  Deploying language agents in real applications demands more than the right answer: an agent must execute a multi-step business process correctly, follow domain-specific rules, and interact with a user across a dialogue, where the gap betwee…

• Towards User Simulators That Stay On Task And Still Sound Natural
  Mustafa Omer Gul, Philippe Laban, Tanya Goyal, Jennifer Neville · arXiv · Oct 22, 2026

  Users increasingly rely on AI systems for extended, multi-turn tasks, yet evidence indicates that LLM-based system performance degrades over prolonged interaction. To evaluate and improve AI assistants in such settings, we need user simulat…

• How Different, or Different How? Stance Granularity in Viewpoint Selection for Dialog Systems that Engage Users with Alternative Views
  Morita Tarvirdians, Reeve Lorena, Catharine Oertel · arXiv · Oct 22, 2026

  Systems that aim to help a user engage with viewpoints other than their own have to decide how different those viewpoints should be. Viewpoints are mainly represented on a scalar scale, too coarse to distinguish viewpoints that disagree wit…

• When LLMs Forget What They Believe: Characterizing State Integrity Collapse in Long-Horizon Dialogues
  Yancheng Zhu, Yifan Yuan · arXiv · Oct 22, 2026

  Large language models can repeat an instruction while failing to keep obeying it. We study this recall-compliance dissociation in long-horizon dialogue and define State Integrity Collapse: a model preserves a stated constraint in memory but…

• From Clinical Judgment to Checkable Rules: Clinician-Led Guardrails for Mental-Health Chatbots
  Chenhan Lyu, Kit Wislocki, Sarah Elizabeth Stoeckl, Maitreyi Sinha et al. · arXiv · Oct 22, 2026

  Large language models (LLMs) deployed in mental-health contexts can be evaluated for safety failures, but the resulting judgments are often difficult to inspect or explain. Common approaches to improving safety rely on prompt engineering, L…

• Dialogue Act Script: A Structured Framework for Generating Multilingual and Multicultural Dialogues
  [object Object], [object Object], [object Object], [object Object] · Dialogue & Discourse · Oct 22, 2026

  Non-English dialogue datasets are scarce, and models are often trained or evaluated on translations of English-language dialogues, an approach which can introduce artifacts that reduce their naturalness and cultural appropriateness. This wo…

• CulturalRiddles: A Multicultural Benchmark of Riddles
  My Chiffon Nguyen, Tianyi Hu, Vinod Anbalagan, Henry Gagnier et al. · arXiv · Oct 21, 2026

  As LLMs expand their language coverage, evaluating how well they understand and represent diverse cultures becomes increasingly important. However, many benchmarks remain English-centric, with limited cultural coverage and a focus on factua…

• Beyond Small Talk: Modeling Disclosure Trajectories in Human-AI Conversation
  Keith Kwok, Wanting Ning, Tej Deep Pala, Desmond C. Ong et al. · arXiv · Oct 21, 2026

  Recently, we see a rise in conversational agents as a form of social and emotional support, where disclosure will unfold over time. Yet, current evaluations of these agents typically examine isolated conversational states. In analyses of na…

• EviDial: When Correct Depression Predictions Lack Evidence
  Junjie Xu, Jin Zhu, Yuzhe Yang, Luhan Wang et al. · arXiv · Oct 20, 2026

  Depression dialogue benchmarks commonly assess models by comparing predicted symptom labels with clinical scale scores. However, a prediction may agree with a benchmark label even when the dialogue lacks enough evidence to justify it. We in…

• Looking Into The Past: The Impact of Context on Detecting Deceptive Statements
  Alex Clay, Ernesto Jimenez-Ruiz, Pranava Madhyastha · arXiv · Oct 19, 2026

  Deception detection typically considers messages in isolation. Previous works in claim verification and role detection have displayed that additional information such as gameplay history is crucial to successful predictions. In this work, w…