Tootfinder

'There should have been a dialogue' — Zelensky on controversial Ukrainian law that sparked protests: https://benborges.xyz/2025/07/25/there-should-have-been-a.html

Today, I’ll give a talk at the workshop “Re-Designing the Modern Religious Bookshelf – A Faculty-Library Dialogue on (Re-)Classifying Religious Literature,” organized by @… and Christian Meyer.

DA-Mamba: Dialogue-aware selective state-space model for multimodal engagement estimation
Shenwei Kang, Xin Zhang, Wen Liu, Bin Li, Yujie Liu, Bo Gao
https://arxiv.org/abs/2509.17711

DA-Mamba: Dialogue-aware selective state-space model for multimodal engagement estimation
Human engagement estimation in conversational scenarios is essential for applications such as adaptive tutoring, remote healthcare assessment, and socially aware human--computer interaction. Engagement is a dynamic, multimodal signal conveyed by facial expressions, speech, gestures, and behavioral cues over time. In this work we introduce DA-Mamba, a dialogue-aware multimodal architecture that replaces attention-heavy dialogue encoders with Mamba-based selective state-space processing to achiev…

A State-Update Prompting Strategy for Efficient and Robust Multi-turn Dialogue
Ziyi Liu
https://arxiv.org/abs/2509.17766 https://arxiv.org/pdf/2509.17766…

A State-Update Prompting Strategy for Efficient and Robust Multi-turn Dialogue
Large Language Models (LLMs) struggle with information forgetting and inefficiency in long-horizon, multi-turn dialogues. To address this, we propose a training-free prompt engineering method, the State-Update Multi-turn Dialogue Strategy. It utilizes "State Reconstruction" and "History Remind" mechanisms to effectively manage dialogue history. Our strategy shows strong performance across multiple multi-hop QA datasets. For instance, on the HotpotQA dataset, it improves the core information fil…

Decoding Instructional Dialogue: Human-AI Collaborative Analysis of Teacher Use of AI Tool at Scale
Alex Liu, Lief Esbenshade, Shawon Sarkar, Victor Tian, Zachary Zhang, Kevin He, Min Sun
https://arxiv.org/abs/2507.17985

Decoding Instructional Dialogue: Human-AI Collaborative Analysis of Teacher Use of AI Tool at Scale
The integration of large language models (LLMs) into educational tools has the potential to substantially impact how teachers plan instruction, support diverse learners, and engage in professional reflection. Yet little is known about how educators actually use these tools in practice and how their interactions with AI can be meaningfully studied at scale. This paper presents a human-AI collaborative methodology for large-scale qualitative analysis of over 140,000 educator-AI messages drawn fro…

My Linux PC and I are venturing back into the Old Republic tonight! Expect epic space battles, questionable dialogue choices, and me probably falling off something tall. Tune into the #SWTOR stream! #StarWarsTheOldRepublic

Agentic Aerial Cinematography: From Dialogue Cues to Cinematic Trajectories
Yifan Lin, Sophie Ziyu Liu, Ran Qi, George Z. Xue, Xinping Song, Chao Qin, Hugh H. -T. Liu
https://arxiv.org/abs/2509.16176

Agentic Aerial Cinematography: From Dialogue Cues to Cinematic Trajectories
We present Agentic Aerial Cinematography: From Dialogue Cues to Cinematic Trajectories (ACDC), an autonomous drone cinematography system driven by natural language communication between human directors and drones. The main limitation of previous drone cinematography workflows is that they require manual selection of waypoints and view angles based on predefined human intent, which is labor-intensive and yields inconsistent performance. In this paper, we propose employing large language models (…

Investigating the Representation of Backchannels and Fillers in Fine-tuned Language Models
Yu Wang, Leyi Lao, Langchu Huang, Gabriel Skantze, Yang Xu, Hendrik Buschmeier
https://arxiv.org/abs/2509.20237

Investigating the Representation of Backchannels and Fillers in Fine-tuned Language Models
Backchannels and fillers are important linguistic expressions in dialogue, but are under-represented in modern transformer-based language models (LMs). Our work studies the representation of them in language models using three fine-tuning strategies. The models are trained on three dialogue corpora in English and Japanese, where backchannels and fillers are preserved and annotated, to investigate how fine-tuning can help LMs learn their representations. We first apply clustering analysis to the…

Learning Contextual Retrieval for Robust Conversational Search
Seunghan Yang, Juntae Lee, Jihwan Bang, Kyuhong Shim, Minsoo Kim, Simyung Chang
https://arxiv.org/abs/2509.19700 h…

Learning Contextual Retrieval for Robust Conversational Search
Effective conversational search demands a deep understanding of user intent across multiple dialogue turns. Users frequently use abbreviations and shift topics in the middle of conversations, posing challenges for conventional retrievers. While query rewriting techniques improve clarity, they often incur significant computational cost due to additional autoregressive steps. Moreover, although LLM-based retrievers demonstrate strong performance, they are not explicitly optimized to track user in…

Nexstar says it will continue to preempt Jimmy Kimmel Live!, "pending assurances that all parties are committed to ... respectful, constructive dialogue" (Ted Johnson/Deadline)
https://deadline.com/2025/09/nexstar-jimmy-kimmel-preemption-1236553268/

Nexstar Stations Will Join Sinclair In Preempting Jimmy Kimmel When Host Returns To ABC Tonight
The late-night host is returning to the air tonight.

Generative AI as a catalyst for democratic Innovation: Enhancing citizen engagement in participatory budgeting
Italo Alberto do Nascimento Sousa, Jorge Machado, Jose Carlos Vaz
https://arxiv.org/abs/2509.19497

Generative AI as a catalyst for democratic Innovation: Enhancing citizen engagement in participatory budgeting
This research examines the role of Generative Artificial Intelligence (AI) in enhancing citizen engagement in participatory budgeting. In response to challenges like declining civic participation and increased societal polarization, the study explores how online political participation can strengthen democracy and promote social equity. By integrating Generative AI into public consultation platforms, the research aims to improve citizen proposal formulation and foster effective dialogue between…

PyTOD: Programmable Task-Oriented Dialogue with Execution Feedback
Alexandru Coca, Bo-Hsiang Tseng, Pete Boothroyd, Jianpeng Cheng, Mark Gaynor, Zhenxing Zhang, Joe Stacey, Tristan Guigue, H\'ector Martinez Alonso, Diarmuid \'O S\'eaghdha, Anders Johannsen
https://arxiv.org/abs/2508.15456…

PyTOD: Programmable Task-Oriented Dialogue with Execution Feedback
Programmable task-oriented dialogue (TOD) agents enable language models to follow structured dialogue policies, but their effectiveness hinges on accurate state tracking. We present PyTOD, an agent that generates executable code to track dialogue state and uses policy and execution feedback for efficient error correction. To this end, PyTOD employs a simple constrained decoding approach, using a language model instead of grammar rules to follow API schemata. This leads to state-of-the-art state…

Emotion-Aware Speech Generation with Character-Specific Voices for Comics
Zhiwen Qian, Jinhua Liang, Huan Zhang
https://arxiv.org/abs/2509.15253 https://ar…

Emotion-Aware Speech Generation with Character-Specific Voices for Comics
This paper presents an end-to-end pipeline for generating character-specific, emotion-aware speech from comics. The proposed system takes full comic volumes as input and produces speech aligned with each character's dialogue and emotional state. An image processing module performs character detection, text recognition, and emotion intensity recognition. A large language model performs dialogue attribution and emotion analysis by integrating visual information with the evolving plot context. Spe…

Talking to...uh...um...Machines: The Impact of Disfluent Speech Agents on Partner Models and Perspective Taking
Rhys Jacka, Paola R. Pe\~na, Sophie Leonard, \'Eva Sz\'ekely, Benjamin R. Cowan
https://arxiv.org/abs/2507.18315

Talking to...uh...um...Machines: The Impact of Disfluent Speech Agents on Partner Models and Perspective Taking
Speech disfluencies play a role in perspective-taking and audience design in human-human communication (HHC), but little is known about their impact in human-machine dialogue (HMD). In an online Namer-Matcher task, sixty-one participants interacted with a speech agent using either fluent or disfluent speech. Participants completed a partner-modelling questionnaire (PMQ) both before and after the task. Post-interaction evaluations indicated that participants perceived the disfluent agent as more…

MMedFD: A Real-world Healthcare Benchmark for Multi-turn Full-Duplex Automatic Speech Recognition
Hongzhao Chen, XiaoYang Wang, Jing Lan, Hexiao Ding, Yufeng Jiang MingHui Yang, DanHui Xu, Jun Luo, Nga-Chun Ng, Gerald W. Y. Cheng, Yunlin Mao, Jung Sun Yoo
https://arxiv.org/abs/2509.19817

MMedFD: A Real-world Healthcare Benchmark for Multi-turn Full-Duplex Automatic Speech Recognition
Automatic speech recognition (ASR) in clinical dialogue demands robustness to full-duplex interaction, speaker overlap, and low-latency constraints, yet open benchmarks remain scarce. We present MMedFD, the first real-world Chinese healthcare ASR corpus designed for multi-turn, full-duplex settings. Captured from a deployed AI assistant, the dataset comprises 5,805 annotated sessions with synchronized user and mixed-channel views, RTTM/CTM timing, and role labels. We introduce a model-agnostic …

Finished "I See You've Called in Dead" by John Kenney and loved it.
Bud Stanley is an obituary writer, adrift after his divorce. After a particularly brutal blind date, Bud has a bit too much to drink and accidentally publishes his own joke obituary. Chaos ensues.
Manages to be witty and funny without being over the top. Really great characters & dialogue, which reveal deep emotional questions about really living & caring for each other.
5/5 stars ⭐⭐⭐⭐…

I See You've Called in Dead
“Razor-sharp, darkly comedic, and emotionally piercing.…

Behind the Blog: 'Free Speech' and Open Dialogue https://www.404media.co/behind-the-blog-free-speech-and-open-dialogue/

Luma AI partners with Adobe to bring its generative video model Ray3 to Firefly's paid users; Ray3 creates highly realistic 10-second videos without dialogue (Steven Zeitchik/The Hollywood Reporter)
https://www.hollywoodreporter.com/business/digi…

Luma AI and Adobe Partner to Distribute New Generative Video Model
Ray3, the companies hope, can become a staple to rival Google

Dialogue Systems Engineering: A Survey and Future Directions
Mikio Nakano, Hironori Takeuchi, Sadahiro Yoshikawa, Yoichi Matsuyama, Kazunori Komatani
https://arxiv.org/abs/2508.02279

Dialogue Systems Engineering: A Survey and Future Directions
This paper proposes to refer to the field of software engineering related to the life cycle of dialogue systems as Dialogue Systems Engineering, and surveys this field while also discussing its future directions. With the advancement of large language models, the core technologies underlying dialogue systems have significantly progressed. As a result, dialogue system technology is now expected to be applied to solving various societal issues and in business contexts. To achieve this, it is impo…

One for all good Americans, appropriately via _Foundation_ season 3 episode 7, "Foundation's End".

LOTUSDIS: A Thai far-field meeting corpus for robust conversational ASR
Pattara Tipaksorn, Sumonmas Thatphithakkul, Vataya Chunwijitra, Kwanchiva Thangthai
https://arxiv.org/abs/2509.18722

MAD: A Benchmark for Multi-Turn Audio Dialogue Fact-Checking
Chaewan Chun, Lysandre Terrisse, Delvin Ce Zhang, Dongwon Lee
https://arxiv.org/abs/2508.12186 https://

MAD: A Benchmark for Multi-Turn Audio Dialogue Fact-Checking
Despite the growing popularity of audio platforms, fact-checking spoken content remains significantly underdeveloped. Misinformation in speech often unfolds across multi-turn dialogues, shaped by speaker interactions, disfluencies, overlapping speech, and emotional tone-factors that complicate both claim detection and verification. Existing datasets fall short by focusing on isolated sentences or text transcripts, without modeling the conversational and acoustic complexity of spoken misinformat…

Highlights from FPF’s July 2025 Technologist Roundtable: AI Unlearning and Technical Guardrails
https://fpf.org/blog/highlights-from-fpfs-july-2025-technologist-roundtable-ai-unlearning-and-technical-guardrails/

Christianity, Nationalism, and Ideology in a Globalized World
https://ift.tt/RLB2aOK
Summer 2026 Vietnamese Language Study with Indiana University Kathleen Evans 09/19/2025 - 9:31am …
via Input 4 RELCFP

Je n'aurais jamais imaginé que la STM baptiserait une station de métro en honneur de Mary Two-Axe Earley.
Texte d'Isabelle Picard paru dans la Presse sur cette militante des droits des femmes des Premières Nations au Canada.
https://www.lapresse.ca/dialog…

Bienvenue à la station Mary-Two-Axe-Earley
La Société de transport de Montréal a dévoilé mardi matin le nom des futures stations du prolongement de la ligne bleue du métro de Montréal.

TaleDiffusion: Multi-Character Story Generation with Dialogue Rendering
Ayan Banerjee, Josep Llad\'os, Umapada Pal, Anjan Dutta
https://arxiv.org/abs/2509.04123 https://

TaleDiffusion: Multi-Character Story Generation with Dialogue Rendering
Text-to-story visualization is challenging due to the need for consistent interaction among multiple characters across frames. Existing methods struggle with character consistency, leading to artifact generation and inaccurate dialogue rendering, which results in disjointed storytelling. In response, we introduce TaleDiffusion, a novel framework for generating multi-character stories with an iterative process, maintaining character consistency, and accurate dialogue assignment via postprocessin…

Enhancing the NAO: Extending Capabilities of Legacy Robots for Long-Term Research
Austin Wilson, Sahar Kapasi, Zane Greene, Alexis E. Block
https://arxiv.org/abs/2509.17760 http…

Enhancing the NAO: Extending Capabilities of Legacy Robots for Long-Term Research
Many research groups face challenges when legacy (unsupported) robotic platforms lose manufacturer support and cannot accommodate modern sensing, speech, and interaction capabilities. We present the Enhanced NAO, a revitalized version of Aldebaran's NAO robot that uses upgraded microphones, RGB-D and thermal cameras, and additional compute resources in a fully self-contained package. This system combines cloud and local models for perception and dialogue, while preserving the NAO's expressive b…

Seeing is Believing: Emotion-Aware Audio-Visual Language Modeling for Expressive Speech Generation
Weiting Tan, Jiachen Lian, Hirofumi Inaguma, Paden Tomasello, Philipp Koehn, Xutai Ma
https://arxiv.org/abs/2508.16188

Seeing is Believing: Emotion-Aware Audio-Visual Language Modeling for Expressive Speech Generation
We present an Audio-Visual Language Model (AVLM) for expressive speech generation by integrating full-face visual cues into a pre-trained expressive speech model. We explore multiple visual encoders and multimodal fusion strategies during pre-training to identify the most effective integration approach. Subsequent fine-tuning on emotion recognition and expressive dialogue tasks yields substantial gains over speech-only baselines (e.g., +5 F1 in emotion recognition). AVLM highlights the value of…

Just finished "The Melancholy of Summer" by Louisa Onomé. It's an excellent book about parental abandonment, rejecting and accepting help, and friendship, set in Toronto. There were a few threads that didn't quite get wrapped up by the end, but the ending wasn't dissatisfying, and the writing is excellent, particularly TV gee dialogue and the narration of Summer's thoughts. I felt like the strategic use of stutters both gave the main character extra vulnerability, but also helped subtly clue the reader into moments where Summer's perception of her interlocutors doesn't match their real feelings. Between this and "Like Home", I feel like Onomé's novels are a bit rough around the edges, yet they're still some of the most enjoyable books I've been reading, probably because she's pours so much humanity into her characters and lets their honest desire for something better rub off on the audience.
#AmReading

Using Medical Algorithms for Task-Oriented Dialogue in LLM-Based Medical Interviews
Rui Reis, Pedro Rangel Henriques, Jo\~ao Ferreira-Coimbra, Eva Oliveira, Nuno F. Rodrigues
https://arxiv.org/abs/2510.12490

Using Medical Algorithms for Task-Oriented Dialogue in LLM-Based Medical Interviews
We developed a task-oriented dialogue framework structured as a Directed Acyclic Graph (DAG) of medical questions. The system integrates: (1) a systematic pipeline for transforming medical algorithms and guidelines into a clinical question corpus; (2) a cold-start mechanism based on hierarchical clustering to generate efficient initial questioning without prior patient information; (3) an expand-and-prune mechanism enabling adaptive branching and backtracking based on patient responses; (4) a t…

This week, GÉANT held its first multistakeholder policy event in Brussels—opening a new chapter in how the GÉANT community and European policy makers can work together to shape the #DigitalTransformation of #Europe.
This event laid the groundwork for an ongoing dialogue between GÉANT, …

The Psychology Sisters
Two professionals on a quest to normalise the dialogue around mental health...
Great Australian Pods Podcast Directory: https://www.greataustralianpods.com/the-psychology-sisters/

"it is undeniable that Kirk was not just a part of the extremely tense, very dangerous national dialogue, he was an accelerationist force whose work to dehumanize LGBTQ people and threaten the free speech of professors, teachers, and school board members around the country has directly put the livelihoods and physical safety of many people in danger. We do no one any favors by ignoring this, even in the immediate aftermath of an assassination like this."
(Original title: Cha…

Charlie Kirk Was Not Practicing Politics the Right Way
The mainstream media seems entirely uninterested in explaining Charlie Kirk's work.

WEST: LLM based Speech Toolkit for Speech Understanding, Generation, and Interaction
Binbin Zhang, Chengdong Liang, Shuai Wang, Xuelong Geng, Zhao Guo, Haoyu Li, Hao Yin, Xipeng Yang, Pengshen Zhang, Changwei Ma, Lei Xie
https://arxiv.org/abs/2509.19902

WEST: LLM based Speech Toolkit for Speech Understanding, Generation, and Interaction
In this paper, we present WEST(WE Speech Toolkit), a speech toolkit based on a large language model (LLM) for speech understanding, generation, and interaction. There are three key features of WEST: 1) Fully LLM-based: Standing on the shoulders of giants by reusing mature architectures, ecosystems (e.g., Hugging Face), and methods (e.g., sequence packing) from large models. 2) Full-stack: Supports tasks such as recognition, synthesis, understanding, dialogue, and multimodal capabilities, with e…

#Madagascar : avant de choisir les personnes, il faut que la direction, la méthodologie et le calendrier soient clairement définis.
Et franchement, dans quelle mesure peut-on faire confiance pour le choix d'un Premier ministre Š des députés qui ont avant tout démontré leur versatilité et qui, plutôt que de défendre des idées, défendent prioritairement leurs fauteuils et tickets carburan…

Autiverse: Eliciting Autistic Adolescents' Daily Narratives through AI-guided Multimodal Journaling
Migyeong Yang, Kyungah Lee, Jinyoung Han, SoHyun Park, Young-Ho Kim
https://arxiv.org/abs/2509.17466

Autiverse: Eliciting Autistic Adolescents' Daily Narratives through AI-guided Multimodal Journaling
Journaling can potentially serve as an effective method for autistic adolescents to improve narrative skills. However, its text-centric nature and high executive functioning demands present barriers to practice. We present Autiverse, an AI-guided multimodal journaling app for tablets that scaffolds storytelling through conversational prompts and visual supports. Autiverse elicits key details through a stepwise dialogue with peer-like, customizable AI and composes them into an editable four-pane…

CISA says "Privatizing the CVE Program would dilute its value as a public good," and that dialogue it has had "opened the door to new relationships, conversations, and valuable feedback about the CVE Program."
CVE Quality for a Cyber Secure Future
http…

Analyzing Undergraduate Problem-Solving in Physics Through Interaction With an AI Chatbot
Syed Furqan Abbas Hashmi, N. Sanjay Rebello
https://arxiv.org/abs/2508.14778 https://…

Analyzing Undergraduate Problem-Solving in Physics Through Interaction With an AI Chatbot
Providing individualized scaffolding for physics problem solving at scale remains an instructional challenge. We investigate (1) students' perceptions of a Socratic Artificial Intelligence (AI) chatbot's impact on problem-solving skills and confidence and (2) how the specificity of students' questions during tutoring relates to performance. We deployed a custom Socratic AI chatbot in a large-enrollment introductory mechanics course at a Midwestern public university, logging full dialogue transc…

I do not understand how #2FA on my company laptop works. At random, far-apart times a nondescript dialogue pops up out of nowhere asking me to enter a number in the authenticator app.
Why not ask for the second factor when I log into Windows (the first time of the day)? At least when there is no (known) network?
It also feels like it would not be terribly hard to produce something like…

Tree-based Dialogue Reinforced Policy Optimization for Red-Teaming Attacks
Ruohao Guo, Afshin Oroojlooy, Roshan Sridhar, Miguel Ballesteros, Alan Ritter, Dan Roth
https://arxiv.org/abs/2510.02286

Tree-based Dialogue Reinforced Policy Optimization for Red-Teaming Attacks
Despite recent rapid progress in AI safety, current large language models remain vulnerable to adversarial attacks in multi-turn interaction settings, where attackers strategically adapt their prompts across conversation turns and pose a more critical yet realistic challenge. Existing approaches that discover safety vulnerabilities either rely on manual red-teaming with human experts or employ automated methods using pre-defined templates and human-curated attack data, with most focusing on sin…

Luma AI partners with Adobe to bring its generative video model Ray3 to Firefly's paid users; Ray3 creates highly realistic 10-second videos without dialogue (Steven Zeitchik/The Hollywood Reporter)
https://www.hollywoodreporter.com/business/digi…

Luma AI and Adobe Partner to Distribute New Generative Video Model
Ray3, the companies hope, can become a staple to rival Google

Ask-to-Clarify: Resolving Instruction Ambiguity through Multi-turn Dialogue
Xingyao Lin, Xinghao Zhu, Tianyi Lu, Sicheng Xie, Hui Zhang, Xipeng Qiu, Zuxuan Wu, Yu-Gang Jiang
https://arxiv.org/abs/2509.15061

Ask-to-Clarify: Resolving Instruction Ambiguity through Multi-turn Dialogue
The ultimate goal of embodied agents is to create collaborators that can interact with humans, not mere executors that passively follow instructions. This requires agents to communicate, coordinate, and adapt their actions based on human feedback. Recently, advances in VLAs have offered a path toward this goal. However, most current VLA-based embodied agents operate in a one-way mode: they receive an instruction and execute it without feedback. This approach fails in real-world scenarios where …

Open-Universe Assistance Games
Rachel Ma, Jingyi Qu, Andreea Bobu, Dylan Hadfield-Menell
https://arxiv.org/abs/2508.15119 https://arxiv.org/pdf/2508.15119

Open-Universe Assistance Games
Embodied AI agents must infer and act in an interpretable way on diverse human goals and preferences that are not predefined. To formalize this setting, we introduce Open-Universe Assistance Games (OU-AGs), a framework where the agent must reason over an unbounded and evolving space of possible goals. In this context, we introduce GOOD (GOals from Open-ended Dialogue), a data-efficient, online method that extracts goals in the form of natural language during an interaction with a human, and inf…

LECTURE: "To Everything a Season: Nostra Aetate Sixty Years On" (HYBRID)
https://ift.tt/TUxSoAH
H-Diplo Roundtable XXV-12 on Fall, _Dien Bien Phu: Un coin d’Enfer_ H-Diplo Roundtable…
via Input 4 RELCFP

From SFU
#Vancouver Climate Day
On Friday, September 26, join the SFU Morris J. Wosk Centre for Dialogue for a day dedicated to collaboration and learning about the amazing climate action work taking place across the wider Vancouver community. Featuring workshops, panels, showcases, networking and much more, this one-day event brings together researchers, policy leaders, action leaders and …

Series B, Episode 10 - Voice from the Past
AVON: I'm sorry to have to inform you that he is himself all right.
[End of episode. Roll credits.]
https://blake.torpidity.net/m/210/623 B7B3

I kinda hate marketing . . . but I enjoy supporting talented artists. I worked with two artists to get some promotional art for .Liar, Cheater, Sinner, Saint.' Here's the art from @gargoyle.pastures that inspired me to throw away the cover I had already bought and use one of these panels instead. Links to the full panels are up at https://www.

Data-Aware Socratic Query Refinement in Database Systems
Ruiyuan Zhang, Chrysanthi Kosyfaki, Xiaofang Zhou
https://arxiv.org/abs/2508.05061 https://arxiv.o…

Data-Aware Socratic Query Refinement in Database Systems
In this paper, we propose Data-Aware Socratic Guidance (DASG), a dialogue-based query enhancement framework that embeds \linebreak interactive clarification as a first-class operator within database systems to resolve ambiguity in natural language queries. DASG treats dialogue as an optimization decision, asking clarifying questions only when the expected execution cost reduction exceeds the interaction overhead. The system quantifies ambiguity through linguistic fuzziness, schema grounding con…

ding-01 :ARG0: An AMR Corpus for Spontaneous French Dialogue
Jeongwoo Kang, Maria Boritchev, Maximin Coavoux
https://arxiv.org/abs/2508.12819 https://arxiv…

ding-01 :ARG0: An AMR Corpus for Spontaneous French Dialogue
We present our work to build a French semantic corpus by annotating French dialogue in Abstract Meaning Representation (AMR). Specifically, we annotate the DinG corpus, consisting of transcripts of spontaneous French dialogues recorded during the board game Catan. As AMR has insufficient coverage of the dynamics of spontaneous speech, we extend the framework to better represent spontaneous speech and sentence structures specific to French. Additionally, to support consistent annotation, we prov…

Conversational DNA: A New Visual Language for Understanding Dialogue Structure in Human and AI
Baihan Lin
https://arxiv.org/abs/2508.07520 https://arxiv.or…

Conversational DNA: A New Visual Language for Understanding Dialogue Structure in Human and AI
What if the patterns hidden within dialogue reveal more about communication than the words themselves? We introduce Conversational DNA, a novel visual language that treats any dialogue -- whether between humans, between human and AI, or among groups -- as a living system with interpretable structure that can be visualized, compared, and understood. Unlike traditional conversation analysis that reduces rich interaction to statistical summaries, our approach reveals the temporal architecture of d…

Research on Conversational Recommender System Considering Consumer Types
Yaying Luo, Hui Fang, Zhu Sun
https://arxiv.org/abs/2508.13209 https://arxiv.org/p…

Research on Conversational Recommender System Considering Consumer Types
Conversational Recommender Systems (CRS) provide personalized services through multi-turn interactions, yet most existing methods overlook users' heterogeneous decision-making styles and knowledge levels, which constrains both accuracy and efficiency. To address this gap, we propose CT-CRS (Consumer Type-Enhanced Conversational Recommender System), a framework that integrates consumer type modeling into dialogue recommendation. Based on consumer type theory, we define four user categories--depe…

The local indie theater was showing Terminator 2 tonight as part of its summer blockbuster series. The boy is off to college next week, but wanted to see it with me. ❤️
Mostly still holds up well. Some of the dialogue is pretty over the top, but he enjoyed it. I would have enjoyed it no matter what, having him along for it.
https://ca…

Terminator 2: Judgment Day
It's nothing personal.

Christianity, Nationalism, and Ideology in a Globalized World
https://ift.tt/oO4zvAL
Summer 2026 Vietnamese Language Study with Indiana University Kathleen Evans 09/19/2025 - 9:31am …
via Input 4 RELCFP

Prepared mind, fast response: A temporal decoupling framework for adaptive knowledge orchestration in open-domain dialogue
Jinling Gan, Churong Liang, Runnan Li
https://arxiv.org/abs/2510.08175

Prepared mind, fast response: A temporal decoupling framework for adaptive knowledge orchestration in open-domain dialogue
The latency-quality tradeoff is a fundamental constraint in open-domain dialogue AI systems, since comprehensive knowledge access necessitates prohibitive response delays. Contemporary approaches offer two inadequate solutions: lightweight instruct models achieve sub-second latency but lack reasoning depth, while tool-augmented ReAct agents enhance factuality through external knowledge at the cost of synchronous execution that blocks interaction during re- trieval processes. PMFR is thus propos…

SSL-SSAW: Self-Supervised Learning with Sigmoid Self-Attention Weighting for Question-Based Sign Language Translation
Zekang Liu, Wei Feng, Fanhua Shang, Lianyu Hu, Jichao Feng, Liqing Gao
https://arxiv.org/abs/2509.14036

SSL-SSAW: Self-Supervised Learning with Sigmoid Self-Attention Weighting for Question-Based Sign Language Translation
Sign Language Translation (SLT) bridges the communication gap between deaf people and hearing people, where dialogue provides crucial contextual cues to aid in translation. Building on this foundational concept, this paper proposes Question-based Sign Language Translation (QB-SLT), a novel task that explores the efficient integration of dialogue. Unlike gloss (sign language transcription) annotations, dialogue naturally occurs in communication and is easier to annotate. The key challenge lies i…

FireRedTTS-2: Towards Long Conversational Speech Generation for Podcast and Chatbot
Kun Xie, Feiyu Shen, Junjie Li, Fenglong Xie, Xu Tang, Yao Hu
https://arxiv.org/abs/2509.02020

FireRedTTS-2: Towards Long Conversational Speech Generation for Podcast and Chatbot
Current dialogue generation approaches typically require the complete dialogue text before synthesis and produce a single, inseparable speech containing all voices, making them unsuitable for interactive chat; moreover, they suffer from unstable synthesis, inaccurate speaker transitions, and incoherent prosody. In this work, we present FireRedTTS-2, a long-form streaming TTS system for multi-speaker dialogue generation, delivering stable, natural speech with reliable speaker switching and conte…

Hey, wait a minute: on at-issue sensitivity in Language Models
Sanghee J. Kim, Kanishka Misra
https://arxiv.org/abs/2510.12740 https://arxiv.org/pdf/2510.1…

Hey, wait a minute: on at-issue sensitivity in Language Models
Evaluating the naturalness of dialogue in language models (LMs) is not trivial: notions of 'naturalness' vary, and scalable quantitative metrics remain limited. This study leverages the linguistic notion of 'at-issueness' to assess dialogue naturalness and introduces a new method: Divide, Generate, Recombine, and Compare (DGRC). DGRC (i) divides a dialogue as a prompt, (ii) generates continuations for subparts using LMs, (iii) recombines the dialogue and continuations, and (iv) compares the lik…

DialoSpeech: Dual-Speaker Dialogue Generation with LLM and Flow Matching
Hanke Xie, Dake Guo, Chengyou Wang, Yue Li, Wenjie Tian, Xinfa Zhu, Xinsheng Wang, Xiulin Li, Guanqiong Miao, Bo Liu, Lei Xie
https://arxiv.org/abs/2510.08373

DialoSpeech: Dual-Speaker Dialogue Generation with LLM and Flow Matching
Recent advances in text-to-speech (TTS) synthesis, particularly those leveraging large language models (LLMs), have significantly improved expressiveness and naturalness. However, generating human-like, interactive dialogue speech remains challenging. Current systems face limitations due to the scarcity of dual-track data and difficulties in achieving naturalness, contextual coherence, and interactional dynamics, such as turn-taking, overlapping speech, and speaker consistency, in multi-turn co…

STEP: Stepwise Curriculum Learning for Context-Knowledge Fusion in Conversational Recommendation
Zhenye Yang, Jinpeng Chen, Huan Li, Xiongnan Jin, Xuanyang Li, Junwei Zhang, Hongbo Gao, Kaimin Wei, Senzhang Wang
https://arxiv.org/abs/2508.10669

STEP: Stepwise Curriculum Learning for Context-Knowledge Fusion in Conversational Recommendation
Conversational recommender systems (CRSs) aim to proactively capture user preferences through natural language dialogue and recommend high-quality items. To achieve this, CRS gathers user preferences via a dialog module and builds user profiles through a recommendation module to generate appropriate recommendations. However, existing CRS faces challenges in capturing the deep semantics of user preferences and dialogue context. In particular, the efficient integration of external knowledge graph…

When AI Gets Persuaded, Humans Follow: Inducing the Conformity Effect in Persuasive Dialogue
Rikuo Sasaki, Michimasa Inaba
https://arxiv.org/abs/2510.04229 https://

When AI Gets Persuaded, Humans Follow: Inducing the Conformity Effect in Persuasive Dialogue
Recent advancements in AI have highlighted its application in captology, the field of using computers as persuasive technologies. We hypothesized that the "conformity effect," where individuals align with others' actions, also occurs with AI agents. This study verifies this hypothesis by introducing a "Persuadee Agent" that is persuaded alongside a human participant in a three-party persuasive dialogue with a Persuader Agent. We conducted a text-based dialogue experiment with human participants…

Think, Verbalize, then Speak: Bridging Complex Thoughts and Comprehensible Speech
Sang Hoon Woo, Sehun Lee, Kang-wook Kim, Gunhee Kim
https://arxiv.org/abs/2509.16028 https://…

Think, Verbalize, then Speak: Bridging Complex Thoughts and Comprehensible Speech
Spoken dialogue systems increasingly employ large language models (LLMs) to leverage their advanced reasoning capabilities. However, direct application of LLMs in spoken communication often yield suboptimal results due to mismatches between optimal textual and verbal delivery. While existing approaches adapt LLMs to produce speech-friendly outputs, their impact on reasoning performance remains underexplored. In this work, we propose Think-Verbalize-Speak, a framework that decouples reasoning fr…

Modeling shopper interest broadness with entropy-driven dialogue policy in the context of arbitrarily large product catalogs
Firas Jarboui, Issa Memari
https://arxiv.org/abs/2509.06185

Modeling shopper interest broadness with entropy-driven dialogue policy in the context of arbitrarily large product catalogs
Conversational recommender systems promise rich interactions for e-commerce, but balancing exploration (clarifying user needs) and exploitation (making recommendations) remains challenging, especially when deploying large language models (LLMs) with vast product catalogs. We address this challenge by modeling the breadth of user interest via the entropy of retrieval score distributions. Our method uses a neural retriever to fetch relevant items for a user query and computes the entropy of the r…

First Ask Then Answer: A Framework Design for AI Dialogue Based on Supplementary Questioning with Large Language Models
Chuanruo Fu, Yuncheng Du
https://arxiv.org/abs/2508.08308

First Ask Then Answer: A Framework Design for AI Dialogue Based on Supplementary Questioning with Large Language Models
Large Language Models (LLMs) often struggle to deliver accurate and actionable answers when user-provided information is incomplete or ill-specified. We propose a new interaction paradigm, First Ask Then Answer (FATA), in which, through prompt words, LLMs are guided to proactively generate multidimensional supplementary questions for users prior to response generation. Subsequently, by integrating user-provided supplementary information with the original query through sophisticated prompting te…

LECTURE: "To Everything a Season: Nostra Aetate Sixty Years On" (HYBRID)
https://ift.tt/cK9Shnq
Prof. Ruth Halperin-Kaddari, LLM, JSD: "Recognition and Justice for Victims of Sexual Violence in…
via Input 4 RELCFP

Multi-Intent Recognition in Dialogue Understanding: A Comparison Between Smaller Open-Source LLMs
Adnan Ahmad, Philine Kowol, Stefan Hillmann, Sebastian M\"oller
https://arxiv.org/abs/2509.10010

Multi-Intent Recognition in Dialogue Understanding: A Comparison Between Smaller Open-Source LLMs
In this paper, we provide an extensive analysis of multi-label intent classification using Large Language Models (LLMs) that are open-source, publicly available, and can be run in consumer hardware. We use the MultiWOZ 2.1 dataset, a benchmark in the dialogue system domain, to investigate the efficacy of three popular open-source pre-trained LLMs, namely LLama2-7B-hf, Mistral-7B-v0.1, and Yi-6B. We perform the classification task in a few-shot setup, giving 20 examples in the prompt with some i…

Replaced article(s) found for cs.HC. https://arxiv.org/list/cs.HC/new
[1/1]:
- Script-Strategy Aligned Generation: Aligning LLMs with Expert-Crafted Dialogue Scripts and Therap...
Xin Sun, Jan de Wit, Zhuying Li, Jiahuan Pei, Abdallah El Ali, Jos A. Bosch

Can LLMs Judge Debates? Evaluating Non-Linear Reasoning via Argumentation Theory Semantics
Reza Sanayei, Srdjan Vesic, Eduardo Blanco, Mihai Surdeanu
https://arxiv.org/abs/2509.15739

Can LLMs Judge Debates? Evaluating Non-Linear Reasoning via Argumentation Theory Semantics
Large Language Models (LLMs) excel at linear reasoning tasks but remain underexplored on non-linear structures such as those found in natural debates, which are best expressed as argument graphs. We evaluate whether LLMs can approximate structured reasoning from Computational Argumentation Theory (CAT). Specifically, we use Quantitative Argumentation Debate (QuAD) semantics, which assigns acceptability scores to arguments based on their attack and support relations. Given only dialogue-formatte…

LECTURE: "To Everything a Season: Nostra Aetate Sixty Years On" (HYBRID) https://networks.h-net.org/group/announcements/20129194/lecture-everything-season-nostra-aetate-sixty-years-hybrid

fCrit: A Visual Explanation System for Furniture Design Creative Support
Vuong Nguyen, Gabriel Vigliensoni
https://arxiv.org/abs/2508.12416 https://arxiv.o…

fCrit: A Visual Explanation System for Furniture Design Creative Support
We introduce fCrit, a dialogue-based AI system designed to critique furniture design with a focus on explainability. Grounded in reflective learning and formal analysis, fCrit employs a multi-agent architecture informed by a structured design knowledge base. We argue that explainability in the arts should not only make AI reasoning transparent but also adapt to the ways users think and talk about their designs. We demonstrate how fCrit supports this process by tailoring explanations to users' d…

Overview of Dialog System Evaluation Track: Dimensionality, Language, Culture and Safety at DSTC 12
John Mendon\c{c}a, Lining Zhang, Rahul Mallidi, Alon Lavie, Isabel Trancoso, Luis Fernando D'Haro, Jo\~ao Sedoc
https://arxiv.org/abs/2509.13569

Overview of Dialog System Evaluation Track: Dimensionality, Language, Culture and Safety at DSTC 12
The rapid advancement of Large Language Models (LLMs) has intensified the need for robust dialogue system evaluation, yet comprehensive assessment remains challenging. Traditional metrics often prove insufficient, and safety considerations are frequently narrowly defined or culturally biased. The DSTC12 Track 1, "Dialog System Evaluation: Dimensionality, Language, Culture and Safety," is part of the ongoing effort to address these critical gaps. The track comprised two subtasks: (1) Dialogue-le…

CPO: Addressing Reward Ambiguity in Role-playing Dialogue via Comparative Policy Optimization
Xinge Ye, Rui Wang, Yuchuan Wu, Victor Ma, Feiteng Fang, Fei Huang, Yongbin Li
https://arxiv.org/abs/2508.09074

CPO: Addressing Reward Ambiguity in Role-playing Dialogue via Comparative Policy Optimization
Reinforcement Learning Fine-Tuning (RLFT) has achieved notable success in tasks with objectively verifiable answers (e.g., code generation, mathematical reasoning), yet struggles with open-ended subjective tasks like role-playing dialogue. Traditional reward modeling approaches, which rely on independent sample-wise scoring, face dual challenges: subjective evaluation criteria and unstable reward signals.Motivated by the insight that human evaluation inherently combines explicit criteria with i…

Automated Classification of Tutors' Dialogue Acts Using Generative AI: A Case Study Using the CIMA Corpus
Liqun He, Jiaqi Xu
https://arxiv.org/abs/2509.09125 https://…

Automated Classification of Tutors' Dialogue Acts Using Generative AI: A Case Study Using the CIMA Corpus
This study explores the use of generative AI for automating the classification of tutors' Dialogue Acts (DAs), aiming to reduce the time and effort required by traditional manual coding. This case study uses the open-source CIMA corpus, in which tutors' responses are pre-annotated into four DA categories. Both GPT-3.5-turbo and GPT-4 models were tested using tailored prompts. Results show that GPT-4 achieved 80% accuracy, a weighted F1-score of 0.81, and a Cohen's Kappa of 0.74, surpassing base…

Schema-Guided Response Generation using Multi-Frame Dialogue State for Motivational Interviewing Systems
Jie Zeng, Yukiko I. Nakano
https://arxiv.org/abs/2508.20635 https://

Schema-Guided Response Generation using Multi-Frame Dialogue State for Motivational Interviewing Systems
The primary goal of Motivational Interviewing (MI) is to help clients build their own motivation for behavioral change. To support this in dialogue systems, it is essential to guide large language models (LLMs) to generate counselor responses aligned with MI principles. By employing a schema-guided approach, this study proposes a method for updating multi-frame dialogue states and a strategy decision mechanism that dynamically determines the response focus in a manner grounded in MI principles.…

Christianity, Nationalism, and Ideology in a Globalized World
https://ift.tt/tSUZMBE
TOC The Asia Pacific Journal of Anthropology, vol 18, 5 (2017) …
via Input 4 RELCFP https://

Stream RAG: Instant and Accurate Spoken Dialogue Systems with Streaming Tool Usage
Siddhant Arora, Haidar Khan, Kai Sun, Xin Luna Dong, Sajal Choudhary, Seungwhan Moon, Xinyuan Zhang, Adithya Sagar, Surya Teja Appini, Kaushik Patnaik, Sanat Sharma, Shinji Watanabe, Anuj Kumar, Ahmed Aly, Yue Liu, Florian Metze, Zhaojiang Lin
https://arxiv.…

Stream RAG: Instant and Accurate Spoken Dialogue Systems with Streaming Tool Usage
End-to-end speech-in speech-out dialogue systems are emerging as a powerful alternative to traditional ASR-LLM-TTS pipelines, generating more natural, expressive responses with significantly lower latency. However, these systems remain prone to hallucinations due to limited factual grounding. While text-based dialogue systems address this challenge by integrating tools such as web search and knowledge graph APIs, we introduce the first approach to extend tool use directly into speech-in speech-…

ProactiveEval: A Unified Evaluation Framework for Proactive Dialogue Agents
Tianjian Liu, Fanqi Wan, Jiajian Guo, Xiaojun Quan
https://arxiv.org/abs/2508.20973 https://

ProactiveEval: A Unified Evaluation Framework for Proactive Dialogue Agents
Proactive dialogue has emerged as a critical and challenging research problem in advancing large language models (LLMs). Existing works predominantly focus on domain-specific or task-oriented scenarios, which leads to fragmented evaluations and limits the comprehensive exploration of models' proactive conversation abilities. In this work, we propose ProactiveEval, a unified framework designed for evaluating proactive dialogue capabilities of LLMs. This framework decomposes proactive dialogue in…

Auto-Slides: An Interactive Multi-Agent System for Creating and Customizing Research Presentations
Yuheng Yang, Wenjia Jiang, Yang Wang, Yiwei Wang, Chi Zhang
https://arxiv.org/abs/2509.11062

Auto-Slides: An Interactive Multi-Agent System for Creating and Customizing Research Presentations
The rapid progress of large language models (LLMs) has opened new opportunities for education. While learners can interact with academic papers through LLM-powered dialogue, limitations still exist: absence of structured organization and high text reliance can impede systematic understanding and engagement with complex concepts. To address these challenges, we propose Auto-Slides, an LLM-driven system that converts research papers into pedagogically structured, multimodal slides (e.g., diagrams…

A Comparative Study of Decoding Strategies in Medical Text Generation
Oriana Presacan, Alireza Nik, Vajira Thambawita, Bogdan Ionescu, Michael Riegler
https://arxiv.org/abs/2508.13580

A Comparative Study of Decoding Strategies in Medical Text Generation
Large Language Models (LLMs) rely on various decoding strategies to generate text, and these choices can significantly affect output quality. In healthcare, where accuracy is critical, the impact of decoding strategies remains underexplored. We investigate this effect in five open-ended medical tasks, including translation, summarization, question answering, dialogue, and image captioning, evaluating 11 decoding strategies with medically specialized and general-purpose LLMs of different sizes. …

Sycophancy under Pressure: Evaluating and Mitigating Sycophantic Bias via Adversarial Dialogues in Scientific QA
Kaiwei Zhang, Qi Jia, Zijian Chen, Wei Sun, Xiangyang Zhu, Chunyi Li, Dandan Zhu, Guangtao Zhai
https://arxiv.org/abs/2508.13743

Sycophancy under Pressure: Evaluating and Mitigating Sycophantic Bias via Adversarial Dialogues in Scientific QA
Large language models (LLMs), while increasingly used in domains requiring factual rigor, often display a troubling behavior: sycophancy, the tendency to align with user beliefs regardless of correctness. This tendency is reinforced by preference-based alignment techniques that optimize for user satisfaction but can undermine truthfulness. While relatively benign in casual dialogue, sycophancy poses serious risks in high-stakes settings such as scientific question answering (QA), where model ou…

The Speech-LLM Takes It All: A Truly Fully End-to-End Spoken Dialogue State Tracking Approach
Nizar El Ghazal, Antoine Caubri\`ere, Valentin Vielzeuf
https://arxiv.org/abs/2510.09424

The Speech-LLM Takes It All: A Truly Fully End-to-End Spoken Dialogue State Tracking Approach
This paper presents a comparative study of context management strategies for end-to-end Spoken Dialog State Tracking using Speech-LLMs. We systematically evaluate traditional multimodal context (combining text history and spoken current turn), full spoken history, and compressed spoken history approaches. Our experiments on the SpokenWOZ corpus demonstrate that providing the full spoken conversation as input yields the highest performance among models of similar size, significantly surpassing p…

The Siren Song of LLMs: How Users Perceive and Respond to Dark Patterns in Large Language Models
Yike Shi (Diane), Qing Xiao (Diane), Qing (Diane), Hu, Hong Shen, Hua Shen
https://arxiv.org/abs/2509.10830

The Siren Song of LLMs: How Users Perceive and Respond to Dark Patterns in Large Language Models
Large language models can influence users through conversation, creating new forms of dark patterns that differ from traditional UX dark patterns. We define LLM dark patterns as manipulative or deceptive behaviors enacted in dialogue. Drawing on prior work and AI incident reports, we outline a diverse set of categories with real-world examples. Using them, we conducted a scenario-based study where participants (N=34) compared manipulative and neutral LLM responses. Our results reveal that recog…

QUARTZ : QA-based Unsupervised Abstractive Refinement for Task-oriented Dialogue Summarization
Mohamed Imed Eddine Ghebriout (Universite de Lorraine, CNRS, Inria, LORIA, Nancy, France), Ga\"el Guibon (Universite de Lorraine, CNRS, Inria, LORIA, Nancy, France), Ivan Lerner (Inserm, Centre de Recherche des Cordeliers, Universite Paris Cite, Sorbonne Universite, Paris, France), Emmanuel Vincent (Universite de Lorraine, CNRS, Inria, LORIA, Nancy, France)

QUARTZ : QA-based Unsupervised Abstractive Refinement for Task-oriented Dialogue Summarization
Dialogue summarization aims to distill the core meaning of a conversation into a concise text. This is crucial for reducing the complexity and noise inherent in dialogue-heavy applications. While recent approaches typically train language models to mimic human-written summaries, such supervision is costly and often results in outputs that lack task-specific focus limiting their effectiveness in downstream applications, such as medical tasks. In this paper, we propose \app, a framework for task-…

Text-to-SQL Task-oriented Dialogue Ontology Construction
Renato Vukovic, Carel van Niekerk, Michael Heck, Benjamin Ruppik, Hsien-Chin Lin, Shutong Feng, Nurul Lubis, Milica Gasic
https://arxiv.org/abs/2507.23358

Text-to-SQL Task-oriented Dialogue Ontology Construction
Large language models (LLMs) are widely used as general-purpose knowledge sources, but they rely on parametric knowledge, limiting explainability and trustworthiness. In task-oriented dialogue (TOD) systems, this separation is explicit, using an external database structured by an explicit ontology to ensure explainability and controllability. However, building such ontologies requires manual labels or supervised training. We introduce TeQoDO: a Text-to-SQL task-oriented Dialogue Ontology constr…

Replaced article(s) found for cs.HC. https://arxiv.org/list/cs.HC/new
[1/1]:
- Script2Screen: Supporting Dialogue Scriptwriting with Interactive Audiovisual Generation
Zhecheng Wang, Jiaju Ma, Eitan Grinspun, Tovi Grossman, Bryan Wang

Towards Stable and Personalised Profiles for Lexical Alignment in Spoken Human-Agent Dialogue
Keara Schaaij, Roel Boumans, Tibor Bosse, Iris Hendrickx
https://arxiv.org/abs/2509.04104

Towards Stable and Personalised Profiles for Lexical Alignment in Spoken Human-Agent Dialogue
Lexical alignment, where speakers start to use similar words across conversation, is known to contribute to successful communication. However, its implementation in conversational agents remains underexplored, particularly considering the recent advancements in large language models (LLMs). As a first step towards enabling lexical alignment in human-agent dialogue, this study draws on strategies for personalising conversational agents and investigates the construction of stable, personalised le…

Advancing Conversational AI with Shona Slang: A Dataset and Hybrid Model for Digital Inclusion
Happymore Masoka
https://arxiv.org/abs/2509.14249 https://ar…

Advancing Conversational AI with Shona Slang: A Dataset and Hybrid Model for Digital Inclusion
African languages remain underrepresented in natural language processing (NLP), with most corpora limited to formal registers that fail to capture the vibrancy of everyday communication. This work addresses this gap for Shona, a Bantu language spoken in Zimbabwe and Zambia, by introducing a novel Shona--English slang dataset curated from anonymized social media conversations. The dataset is annotated for intent, sentiment, dialogue acts, code-mixing, and tone, and is publicly available at https…

MDSEval: A Meta-Evaluation Benchmark for Multimodal Dialogue Summarization
Yinhong Liu, Jianfeng He, Hang Su, Ruixue Lian, Yi Nian, Jake Vincent, Srikanth Vishnubhotla, Robinson Piramuthu, Saab Mansour
https://arxiv.org/abs/2510.01659

MDSEval: A Meta-Evaluation Benchmark for Multimodal Dialogue Summarization
Multimodal Dialogue Summarization (MDS) is a critical task with wide-ranging applications. To support the development of effective MDS models, robust automatic evaluation methods are essential for reducing both cost and human effort. However, such methods require a strong meta-evaluation benchmark grounded in human annotations. In this work, we introduce MDSEval, the first meta-evaluation benchmark for MDS, consisting image-sharing dialogues, corresponding summaries, and human judgments across …

Hybrid Dialogue State Tracking for Persian Chatbots: A Language Model-Based Approach
Samin Mahdipour Aghabagher, Saeedeh Momtazi
https://arxiv.org/abs/2510.01052 https://…

Hybrid Dialogue State Tracking for Persian Chatbots: A Language Model-Based Approach
Dialogue State Tracking (DST) is an essential element of conversational AI with the objective of deeply understanding the conversation context and leading it toward answering user requests. Due to high demands for open-domain and multi-turn chatbots, the traditional rule-based DST is not efficient enough, since it cannot provide the required adaptability and coherence for human-like experiences in complex conversations. This study proposes a hybrid DST model that utilizes rule-based methods alo…

Chain-of-Thought Reasoning in Streaming Full-Duplex End-to-End Spoken Dialogue Systems
Siddhant Arora, Jinchuan Tian, Hayato Futami, Jiatong Shi, Yosuke Kashiwagi, Emiru Tsunoo, Shinji Watanabe
https://arxiv.org/abs/2510.02066

Chain-of-Thought Reasoning in Streaming Full-Duplex End-to-End Spoken Dialogue Systems
Most end-to-end (E2E) spoken dialogue systems (SDS) rely on voice activity detection (VAD) for turn-taking, but VAD fails to distinguish between pauses and turn completions. Duplex SDS models address this by predicting output continuously, including silence tokens, thus removing the need for explicit VAD. However, they often have complex dual-channel architecture and lag behind cascaded models in semantic reasoning. To overcome these challenges, we propose SCoT: a Streaming Chain-of-Thought (Co…

LLMs and their Limited Theory of Mind: Evaluating Mental State Annotations in Situated Dialogue
Katharine Kowalyshyn, Matthias Scheutz
https://arxiv.org/abs/2509.02292 https://

LLMs and their Limited Theory of Mind: Evaluating Mental State Annotations in Situated Dialogue
What if large language models could not only infer human mindsets but also expose every blind spot in team dialogue such as discrepancies in the team members' joint understanding? We present a novel, two-step framework that leverages large language models (LLMs) both as human-style annotators of team dialogues to track the team's shared mental models (SMMs) and as automated discrepancy detectors among individuals' mental states. In the first step, an LLM generates annotations by identifying SMM…

Replaced article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[1/2]:
- A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems
Zihao Yi, Jiarui Ouyang, Zhe Xu, Yuwen Liu, Tianhao Liao, Haohao Luo, Ying Shen

Mitigating Strategy Preference Bias in Emotional Support Conversation via Uncertainty Estimations
Yougen Zhou, Qin Chen, Ningning Zhou, Jie Zhou, Xingjiao Wu, Liang He
https://arxiv.org/abs/2509.12661 …

Mitigating Strategy Preference Bias in Emotional Support Conversation via Uncertainty Estimations
Emotional support conversation (ESC) aims to alleviate distress through empathetic dialogue, yet large language models (LLMs) face persistent challenges in delivering effective ESC due to low accuracy in strategy planning. Moreover, there is a considerable preference bias towards specific strategies. Prior methods using fine-tuned strategy planners have shown potential in reducing such bias, while the underlying causes of the preference bias in LLMs have not well been studied. To address these …

Synthetic Dialogue Generation for Interactive Conversational Elicitation & Recommendation (ICER)
Moonkyung Ryu, Chih-Wei Hsu, Yinlam Chow, Mohammad Ghavamzadeh, Craig Boutilier
https://arxiv.org/abs/2510.02331

Synthetic Dialogue Generation for Interactive Conversational Elicitation & Recommendation (ICER)
While language models (LMs) offer great potential for conversational recommender systems (CRSs), the paucity of public CRS data makes fine-tuning LMs for CRSs challenging. In response, LMs as user simulators qua data generators can be used to train LM-based CRSs, but often lack behavioral consistency, generating utterance sequences inconsistent with those of any real user. To address this, we develop a methodology for generating natural dialogues that are consistent with a user's underlying sta…

ReSURE: Regularizing Supervision Unreliability for Multi-turn Dialogue Fine-tuning
Yiming Du, Yifan Xiang, Bin Liang, Dahua Lin, Kam-Fai Wong, Fei Tan
https://arxiv.org/abs/2508.19996

ReSURE: Regularizing Supervision Unreliability for Multi-turn Dialogue Fine-tuning
Fine-tuning multi-turn dialogue systems requires high-quality supervision but often suffers from degraded performance when exposed to low-quality data. Supervision errors in early turns can propagate across subsequent turns, undermining coherence and response quality. Existing methods typically address data quality via static prefiltering, which decouples quality control from training and fails to mitigate turn-level error propagation. In this context, we propose ReSURE (Regularizing Supervisio…

Why Synthetic Isn't Real Yet: A Diagnostic Framework for Contact Center Dialogue Generation
Rishikesh Devanathan, Varun Nathan, Ayush Kumar
https://arxiv.org/abs/2508.18210 …

Why Synthetic Isn't Real Yet: A Diagnostic Framework for Contact Center Dialogue Generation
Synthetic transcript generation is critical in contact center domains, where privacy and data scarcity limit model training and evaluation. Unlike prior synthetic dialogue generation work on open-domain or medical dialogues, contact center conversations are goal-oriented, role-asymmetric, and behaviorally complex, featuring disfluencies, ASR noise, and compliance-driven agent actions. In deployments where transcripts are unavailable, standard pipelines still yield derived call attributes such a…

Analyzing Information-Seeking Behaviors in a Hakka AI Chatbot: A Cognitive-Pragmatic Study
Chu-Hsuan Lee, Chen-Chi Chang, Hung-Shin Lee, Yun-Hsiang Hsu, Ching-Yuan Chen
https://arxiv.org/abs/2509.11591

Analyzing Information-Seeking Behaviors in a Hakka AI Chatbot: A Cognitive-Pragmatic Study
With many endangered languages at risk of disappearing, efforts to preserve them now rely more than ever on using technology alongside culturally informed teaching strategies. This study examines user behaviors in TALKA, a generative AI-powered chatbot designed for Hakka language engagement, by employing a dual-layered analytical framework grounded in Bloom's Taxonomy of cognitive processes and dialogue act categorization. We analyzed 7,077 user utterances, each carefully annotated according to…

SGMem: Sentence Graph Memory for Long-Term Conversational Agents
Yaxiong Wu, Yongyue Zhang, Sheng Liang, Yong Liu
https://arxiv.org/abs/2509.21212 https://…

SGMem: Sentence Graph Memory for Long-Term Conversational Agents
Long-term conversational agents require effective memory management to handle dialogue histories that exceed the context window of large language models (LLMs). Existing methods based on fact extraction or summarization reduce redundancy but struggle to organize and retrieve relevant information across different granularities of dialogue and generated memory. We introduce SGMem (Sentence Graph Memory), which represents dialogue as sentence-level graphs within chunked units, capturing associatio…

The Dialogue That Heals: A Comprehensive Evaluation of Doctor Agents' Inquiry Capability
Linlu Gong, Ante Wang, Yunghwei Lai, Weizhi Ma, Yang Liu
https://arxiv.org/abs/2509.24958

The Dialogue That Heals: A Comprehensive Evaluation of Doctor Agents' Inquiry Capability
An effective physician should possess a combination of empathy, expertise, patience, and clear communication when treating a patient. Recent advances have successfully endowed AI doctors with expert diagnostic skills, particularly the ability to actively seek information through inquiry. However, other essential qualities of a good doctor remain overlooked. To bridge this gap, we present MAQuE(Medical Agent Questioning Evaluation), the largest-ever benchmark for the automatic and comprehensive …

Psyche-R1: Towards Reliable Psychological LLMs through Unified Empathy, Expertise, and Reasoning
Chongyuan Dai, Jinpeng Hu, Hongchang Shi, Zhuo Li, Xun Yang, Meng Wang
https://arxiv.org/abs/2508.10848 …

Psyche-R1: Towards Reliable Psychological LLMs through Unified Empathy, Expertise, and Reasoning
Amidst a shortage of qualified mental health professionals, the integration of large language models (LLMs) into psychological applications offers a promising way to alleviate the growing burden of mental health disorders. Recent reasoning-augmented LLMs have achieved remarkable performance in mathematics and programming, while research in the psychological domain has predominantly emphasized emotional support and empathetic dialogue, with limited attention to reasoning mechanisms that are bene…