Tootfinder

La Caisse de dépôt finance-t-elle un génocide Š Gaza ?
https://www.lapresse.ca/dialogue/chroniques/2025-07-10/on-a-pose-la-question-pour-vous/la-caisse-finance-t-elle-un-genocide-a-gaza.php

Learning Japanese with Jouzu: Interaction Outcomes with Stylized Dialogue Fictional Agents
Zackary Rackauckas, Julia Hirschberg
https://arxiv.org/abs/2507.06483

Learning Japanese with Jouzu: Interaction Outcomes with Stylized Dialogue Fictional Agents
This study investigates how stylized, voiced agents shape user interaction in a multimodal language learning environment. We conducted a mixed-methods evaluation of 54 participants interacting with anime-inspired characters powered by large language models and expressive text-to-speech synthesis. These agents responded in Japanese character language, offering users asynchronous, semi-structured conversation in varying speech styles and emotional tones. We analyzed user engagement patterns, perc…

Apple adds a 3x playback option for podcasts in iOS26, an Enhance Dialogue tool to hear speech more clearly, and a puzzle game for Apple News Plus subscribers (Jay Peters/The Verge)
https://www.theverge.com/news/684708/apple-podcasts-speed-news-emoji-game…

Apple turns up the speed on Podcasts and adds a new emoji game to News
Apple will let users listen to podcasts at up to 3x speed in the Podcast app, and Apple News Plus subscribers will be able to play a new Emoji Game.

Dialogue-Based Multi-Dimensional Relationship Extraction from Novels
Yuchen Yan, Hanjie Zhao, Senbin Zhu, Hongde Liu, Zhihong Zhang, Yuxiang Jia
https://arxiv.org/abs/2507.04852

Dialogue-Based Multi-Dimensional Relationship Extraction from Novels
Relation extraction is a crucial task in natural language processing, with broad applications in knowledge graph construction and literary analysis. However, the complex context and implicit expressions in novel texts pose significant challenges for automatic character relationship extraction. This study focuses on relation extraction in the novel domain and proposes a method based on Large Language Models (LLMs). By incorporating relationship dimension separation, dialogue data construction, a…

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…

HyperSumm-RL: A Dialogue Summarization Framework for Modeling Leadership Perception in Social Robots
Subasish Das
https://arxiv.org/abs/2507.04160 https://…

HyperSumm-RL: A Dialogue Summarization Framework for Modeling Leadership Perception in Social Robots
This paper introduces HyperSumm-RL, a hypertext-aware summarization and interaction analysis framework designed to investigate human perceptions of social robot leadership through long-form dialogue. The system utilizes a structured Natural Language Processing (NLP) workflow that combines transformer-based long dialogue summarization, leadership style modeling, and user response analysis, enabling scalable evaluation of social robots in complex human-robot interaction (HRI) settings. Unlike pri…

Spec-TOD: A Specialized Instruction-Tuned LLM Framework for Efficient Task-Oriented Dialogue Systems
Quang-Vinh Nguyen, Quang-Chieu Nguyen, Hoang Pham, Khac-Hoai Nam Bui
https://arxiv.org/abs/2507.04841

Spec-TOD: A Specialized Instruction-Tuned LLM Framework for Efficient Task-Oriented Dialogue Systems
Task-oriented dialogue (TOD) systems facilitate goal-driven interactions between users and machines. While recent advances in deep learning have improved the performance, TOD systems often struggle in low-resource scenarios with limited labeled data. To address this challenge, we propose Spec-TOD, a novel framework designed to train an end-to-end TOD system with limited data. Spec-TOD introduces two main innovations: (i) a novel specialized end-to-end TOD framework that incorporates explicit ta…

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…

Well - now I'm kinda stumped.
(no - the password is not Schrödinger)
(from the folks at emailmeform[.]com)
#stupidpasswordrules

MixAssist: An Audio-Language Dataset for Co-Creative AI Assistance in Music Mixing
Michael Clemens, Ana Marasovi\'c
https://arxiv.org/abs/2507.06329 ht…

MixAssist: An Audio-Language Dataset for Co-Creative AI Assistance in Music Mixing
While AI presents significant potential for enhancing music mixing and mastering workflows, current research predominantly emphasizes end-to-end automation or generation, often overlooking the collaborative and instructional dimensions vital for co-creative processes. This gap leaves artists, particularly amateurs seeking to develop expertise, underserved. To bridge this, we introduce MixAssist, a novel audio-language dataset capturing the situated, multi-turn dialogue between expert and amateu…

WHEN TO ACT, WHEN TO WAIT: Modeling Structural Trajectories for Intent Triggerability in Task-Oriented Dialogue
Yaoyao Qian, Jindan Huang, Yuanli Wang, Simon Yu, Kyrie Zhixuan Zhou, Jiayuan Mao, Mingfu Liang, Hanhan Zhou
https://arxiv.org/abs/2506.01881

WHEN TO ACT, WHEN TO WAIT: Modeling Structural Trajectories for Intent Triggerability in Task-Oriented Dialogue
Task-oriented dialogue systems often face difficulties when user utterances seem semantically complete but lack necessary structural information for appropriate system action. This arises because users frequently do not fully understand their own needs, while systems require precise intent definitions. Current LLM-based agents cannot effectively distinguish between linguistically complete and contextually triggerable expressions, lacking frameworks for collaborative intent formation. We present…

"here's a dialogue I had with Claude" is always half-way between
- man, I was so stoned last night, and, you know, have you wondered about [the bleeding obvious considered profound]..."
and
- "I had the weirdest dream; I was [and then, and then, and, I can't quite remember, but then]..."

This https://arxiv.org/abs/2506.00975 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

NTPP: Generative Speech Language Modeling for Dual-Channel Spoken Dialogue via Next-Token-Pair Prediction
Inspired by the impressive capabilities of GPT-4o, there is growing interest in enabling speech language models (SLMs) to engage in natural, fluid spoken interactions with humans. Recent advancements have led to the development of several SLMs that demonstrate promising results in this area. However, current approaches have yet to fully exploit dual-channel speech data, which inherently captures the structure and dynamics of human conversation. In this work, we systematically explore the use of…

A Topological Semantics of Dialogue: Nerve Structures and Logical Extraction
Andreu Ballus Santacana
https://arxiv.org/abs/2506.00615 https://

A Topological Semantics of Dialogue: Nerve Structures and Logical Extraction
We introduce a concise, topologically-motivated semantics for finite dialogues by mapping each utterance to an open set in a fixed semantic space, building the corresponding nerve complex of joint satisfiability, and extracting fundamental combinatorial invariants: 1. The negative nerve, which enumerates all finite collections of utterances whose opens have empty intersection, providing a straightforward criterion for merging separate transcripts without contradiction. 2. The global int…

ElliottAgents: A Natural Language-Driven Multi-Agent System for Stock Market Analysis and Prediction
Jaros{\l}aw A. Chudziak, Micha{\l} Wawer
https://arxiv.org/abs/2507.03435

ElliottAgents: A Natural Language-Driven Multi-Agent System for Stock Market Analysis and Prediction
This paper presents ElliottAgents, a multi-agent system leveraging natural language processing (NLP) and large language models (LLMs) to analyze complex stock market data. The system combines AI-driven analysis with the Elliott Wave Principle to generate human-comprehensible predictions and explanations. A key feature is the natural language dialogue between agents, enabling collaborative analysis refinement. The LLM-enhanced architecture facilitates advanced language understanding, reasoning, …

"it feels like the hope with generative AI is that no matter how much you may hate it, the goal is to bombard you with its horrors and its excesses so frequently that you become numb to it."
(Original title: I’m Getting Real Tired Of Not Being Able To Trust That A Video Game Doesn’t Have AI Crap In It)
https://

I'm Getting Real Tired Of Not Being Able To Trust That A Video Game Doesn't Have AI Crap In It - Aftermath
It sucks that players are having to scour every asset and line of dialogue

CoVoMix2: Advancing Zero-Shot Dialogue Generation with Fully Non-Autoregressive Flow Matching
Leying Zhang, Yao Qian, Xiaofei Wang, Manthan Thakker, Dongmei Wang, Jianwei Yu, Haibin Wu, Yuxuan Hu, Jinyu Li, Yanmin Qian, Sheng Zhao
https://arxiv.org/abs/2506.00885

CoVoMix2: Advancing Zero-Shot Dialogue Generation with Fully Non-Autoregressive Flow Matching
Generating natural-sounding, multi-speaker dialogue is crucial for applications such as podcast creation, virtual agents, and multimedia content generation. However, existing systems struggle to maintain speaker consistency, model overlapping speech, and synthesize coherent conversations efficiently. In this paper, we introduce CoVoMix2, a fully non-autoregressive framework for zero-shot multi-talker dialogue generation. CoVoMix2 directly predicts mel-spectrograms from multi-stream transcriptio…

Peer Review as Structured Commentary: Immutable Identity, Public Dialogue, and Reproducible Scholarship
Craig Steven Wright
https://arxiv.org/abs/2506.22497

Peer Review as Structured Commentary: Immutable Identity, Public Dialogue, and Reproducible Scholarship
This paper reconceptualises peer review as structured public commentary. Traditional academic validation is hindered by anonymity, latency, and gatekeeping. We propose a transparent, identity-linked, and reproducible system of scholarly evaluation anchored in open commentary. Leveraging blockchain for immutable audit trails and AI for iterative synthesis, we design a framework that incentivises intellectual contribution, captures epistemic evolution, and enables traceable reputational dynamics.…

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.

Why Robots Are Bad at Detecting Their Mistakes: Limitations of Miscommunication Detection in Human-Robot Dialogue
Ruben Janssens, Jens De Bock, Sofie Labat, Eva Verhelst, Veronique Hoste, Tony Belpaeme
https://arxiv.org/abs/2506.20268

Why Robots Are Bad at Detecting Their Mistakes: Limitations of Miscommunication Detection in Human-Robot Dialogue
Detecting miscommunication in human-robot interaction is a critical function for maintaining user engagement and trust. While humans effortlessly detect communication errors in conversations through both verbal and non-verbal cues, robots face significant challenges in interpreting non-verbal feedback, despite advances in computer vision for recognizing affective expressions. This research evaluates the effectiveness of machine learning models in detecting miscommunications in robot dialogue. U…

On Mitigating Data Sparsity in Conversational Recommender Systems
Sixiao Zhang, Mingrui Liu, Cheng Long, Wei Yuan, Hongxu Chen, Xiangyu Zhao, Hongzhi Yin
https://arxiv.org/abs/2507.00479

On Mitigating Data Sparsity in Conversational Recommender Systems
Conversational recommender systems (CRSs) capture user preference through textual information in dialogues. However, they suffer from data sparsity on two fronts: the dialogue space is vast and linguistically diverse, while the item space exhibits long-tail and sparse distributions. Existing methods struggle with (1) generalizing to varied dialogue expressions due to underutilization of rich textual cues, and (2) learning informative item representations under severe sparsity. To address these …

“They’re sacrificing the moral center of Harvard Divinity School,” #Gaza #Palestine #Harvard

How a Harvard initiative on the Israeli-Palestinian conflict collapsed amid antisemitism claims
Former staff of Harvard Divinity School's Religion and Public Life program say it encouraged a healthy dialogue, but critics accused it of antisemitism.

ChatChecker: A Framework for Dialogue System Testing and Evaluation Through Non-cooperative User Simulation
Roman Mayr, Michel Schimpf, Thomas Bohn\'e
https://arxiv.org/abs/2507.16792

ChatChecker: A Framework for Dialogue System Testing and Evaluation Through Non-cooperative User Simulation
While modern dialogue systems heavily rely on large language models (LLMs), their implementation often goes beyond pure LLM interaction. Developers integrate multiple LLMs, external tools, and databases. Therefore, assessment of the underlying LLM alone does not suffice, and the dialogue systems must be tested and evaluated as a whole. However, this remains a major challenge. With most previous work focusing on turn-level analysis, less attention has been paid to integrated dialogue-level quali…

FreeBSD: icons are broken in Geany, GIMP, HandBrake, PDF Arranger, Remmina, and various other applications.
In addition to the four screenshots here in Mastodon:
― https://i.imgur.com/iJ2eKe6.png – the Save As dialogue in Firefox (the File Open dialogue is similarly broken)
―

Rager:
https://github.com/w3c/wcag/issues/4460
Part of my frustration with this 1.2.5 discussion (no gaps means auto-pass a lack of AD) was the earlier assertion that videos always have gaps (ha ha, no:

1.2.3 / 1.2.5 Audio description - No pause · Issue #4460 · w3c/wcag
If a video has no pause in dialogue to provide audio descriptions, is the video considered to meet SC 1.2.3 / 1.2.5 Audio description? Even if the content author want to provide audio descriptions ...

MDC-R: The Minecraft Dialogue Corpus with Reference
Chris Madge, Maris Camilleri, Paloma Carretero Garcia, Mladen Karan, Juexi Shao, Prashant Jayannavar, Julian Hough, Benjamin Roth, Massimo Poesio
https://arxiv.org/abs/2506.22062

MDC-R: The Minecraft Dialogue Corpus with Reference
We introduce the Minecraft Dialogue Corpus with Reference (MDC-R). MDC-R is a new language resource that supplements the original Minecraft Dialogue Corpus (MDC) with expert annotations of anaphoric and deictic reference. MDC's task-orientated, multi-turn, situated dialogue in a dynamic environment has motivated multiple annotation efforts, owing to the interesting linguistic phenomena that this setting gives rise to. We believe it can serve as a valuable resource when annotated with reference,…

This https://arxiv.org/abs/2504.13861 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csHC_…

3MDBench: Medical Multimodal Multi-agent Dialogue Benchmark
Though Large Vision-Language Models (LVLMs) are being actively explored in medicine, their ability to conduct telemedicine consultations combining accurate diagnosis with professional dialogue remains underexplored. In this paper, we present 3MDBench (Medical Multimodal Multi-agent Dialogue Benchmark), an open-source framework for simulating and evaluating LVLM-driven telemedical consultations. 3MDBench simulates patient variability through four temperament-based Patient Agents and an Assessor …

Finished 1923 this week. Doesn't have the elŠn of Yellowstone/1883, esp when it comes to dialogue, but was a very solid ride nonetheless. My favorite thing is how they brought the era to life.
You don't have to have watched anything else to get it, but the other stories fill in context.
That said, I'd start with 1883, to this, to Yellowstone if I was new to it.
#film

1923
Follow a new generation of the Dutton family during the early twentieth century when pandemics, historic drought, the end of Prohibition and the Great Depression all plague the mountain west, and the Duttons who call it home.

UniTalker: Conversational Speech-Visual Synthesis
Yifan Hu, Rui Liu, Yi Ren, Xiang Yin, Haizhou Li
https://arxiv.org/abs/2508.04585 https://arxiv.org/pdf/2…

UniTalker: Conversational Speech-Visual Synthesis
Conversational Speech Synthesis (CSS) is a key task in the user-agent interaction area, aiming to generate more expressive and empathetic speech for users. However, it is well-known that "listening" and "eye contact" play crucial roles in conveying emotions during real-world interpersonal communication. Existing CSS research is limited to perceiving only text and speech within the dialogue context, which restricts its effectiveness. Moreover, speech-only responses further constrain the interact…

Good evening, #pride !
Good evening, love!
I'm sorry but you don't look like you're banned!
***
These are the opening words of Budapest mayor, Gergely #Karácsony, from the green party "Dialogue", addressing the crowd in the city's Pride demonstrat…

This https://arxiv.org/abs/2502.13033 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLO_…

Classical notions of computation and the Hasegawa-Thielecke theorem
In the spirit of the Curry-Howard correspondence between proofs and programs, we define and study a syntax and semantics for classical logic equipped with a computationally involutive negation, using a polarised effect calculus. A main challenge in designing a denotational semantics is to accommodate both call-by-value and call-by-name evaluation strategies, which leads to a failure of associativity of composition. Building on the work of the third author, we devise the notion of dialogue duplo…

What I don't hear from the #establishment #Democrats is any discussion about how to actually reach out and #TalkWithVoters (They talk TO voters, but it's not a dialogue (they talk AT voters?)…

A look at the Catholic Church's decade-long dialogue with Silicon Valley on AI, as Pope Leo prepares to make AI's potential threat to humanity a signature issue (Wall Street Journal)
https://www.wsj.com/tech/ai/pope-leo-ai-te

MEET BIANCA-IOANA MARCU, FPF EUROPE MANAGING DIRECTOR
https://fpf.org/blog/meet-bianca-ioana-marcu-fpf-europe-managing-director/
@…

Response Attack: Exploiting Contextual Priming to Jailbreak Large Language Models
Ziqi Miao, Lijun Li, Yuan Xiong, Zhenhua Liu, Pengyu Zhu, Jing Shao
https://arxiv.org/abs/2507.05248

Response Attack: Exploiting Contextual Priming to Jailbreak Large Language Models
Contextual priming, where earlier stimuli covertly bias later judgments, offers an unexplored attack surface for large language models (LLMs). We uncover a contextual priming vulnerability in which the previous response in the dialogue can steer its subsequent behavior toward policy-violating content. Building on this insight, we propose Response Attack, which uses an auxiliary LLM to generate a mildly harmful response to a paraphrased version of the original malicious query. They are then form…

This https://arxiv.org/abs/2505.22767 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csHC_…

In Dialogue with Intelligence: Rethinking Large Language Models as Collective Knowledge
Large Language Models (LLMs) are typically analysed through architectural, behavioural, or training-data lenses. This article offers a theoretical and experiential re-framing: LLMs as dynamic instantiations of Collective human Knowledge (CK), where intelligence is evoked through dialogue rather than stored statically. Drawing on concepts from neuroscience and AI, and grounded in sustained interaction with ChatGPT-4, I examine emergent dialogue patterns, the implications of fine-tuning, and the …

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…

Chatbots? We solved the same problem tens of thousands years ago, with a simpler and more ecological solution. It is called "talking to oneself" (or "internal dialogue").
Well, unless you're looking for someone more intelligent to talk to. But if all the stupidity from the Internet collected into an #LLM really fits the bill…
#AI

Personalized Socially Assistive Robots With End-to-End Speech-Language Models For Well-Being Support
Mengxue Fu, Zhonghao Shi, Minyu Huang, Siqi Liu, Mina Kian, Yirui Song, Maja J. Matari\'c
https://arxiv.org/abs/2507.14412

Personalized Socially Assistive Robots With End-to-End Speech-Language Models For Well-Being Support
Socially assistive robots (SARs) have shown great potential for supplementing well-being support. However, prior studies have found that existing dialogue pipelines for SARs remain limited in real-time latency, back-channeling, and personalized speech dialogue. Toward addressing these limitations, we propose using integrated end-to-end speech-language models (SLMs) with SARs. This work 1) evaluated the usability of an SLM-enabled SAR dialogue system through a small user study, and 2) identified…

This https://arxiv.org/abs/2506.00618 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

RiOSWorld: Benchmarking the Risk of Multimodal Compter-Use Agents
With the rapid development of multimodal large language models (MLLMs), they are increasingly deployed as autonomous computer-use agents capable of accomplishing complex computer tasks. However, a pressing issue arises: Can the safety risk principles designed and aligned for general MLLMs in dialogue scenarios be effectively transferred to real-world computer-use scenarios? Existing research on evaluating the safety risks of MLLM-based computer-use agents suffers from several limitations: it ei…

No War With Iran Will Erase Israel's Crimes in Gaza. Don't Get Distracted.
Israel has adopted a worldview in which every problem should be solved through force, and the people of Israel have become a collective that admires force and brutality while scorning dialogue and compromise.

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

Can Large Language Models Improve Phishing Defense? A Large-Scale Controlled Experiment on Warning Dialogue Explanations
Federico Maria Cau, Giuseppe Desolda, Francesco Greco, Lucio Davide Spano, Luca Vigan\`o
https://arxiv.org/abs/2507.07916

Can Large Language Models Improve Phishing Defense? A Large-Scale Controlled Experiment on Warning Dialogue Explanations
Phishing has become a prominent risk in modern cybersecurity, often used to bypass technological defences by exploiting predictable human behaviour. Warning dialogues are a standard mitigation measure, but the lack of explanatory clarity and static content limits their effectiveness. In this paper, we report on our research to assess the capacity of Large Language Models (LLMs) to generate clear, concise, and scalable explanations for phishing warnings. We carried out a large-scale between-subj…

Those of you who frequently watch TV shows or movies in languages you don’t understand (e.g. with subtitles):
When you recall dialogue in the show/film, do you remember it in the actual language you heard, or in your native language?

Are You Listening to Me? Fine-Tuning Chatbots for Empathetic Dialogue
Paulo Ricardo Knob, Leonardo Scholler, Juliano Rigatti, Soraia Raupp Musse
https://arxiv.org/abs/2507.02537

Are You Listening to Me? Fine-Tuning Chatbots for Empathetic Dialogue
Conversational agents have made significant progress since ELIZA, expanding their role across various domains, including healthcare, education, and customer service. As these agents become increasingly integrated into daily human interactions, the need for emotional intelligence, particularly empathetic listening, becomes increasingly essential. In this study, we explore how Large Language Models (LLMs) respond when tasked with generating emotionally rich interactions. Starting from a small dat…

I think this tedious reviewer needs to see more "lush landscapes, epic struggles, pointed political allegories and delicious, disgusting monsters" in The Sandman ->
The Sandman season two review – Neil Gaiman’s emo drama is so pretentious it ruins everything | Television | The Guardian

And that's how you do it 🎤🗑️ #AIChatBot

Optimizing Storytelling, Improving Audience Retention, and Reducing Waste in the Entertainment Industry
Andrew Cornfeld, Ashley Miller, Mercedes Mora-Figueroa, Kurt Samuels, Anthony Palomba
https://arxiv.org/abs/2506.00076

Optimizing Storytelling, Improving Audience Retention, and Reducing Waste in the Entertainment Industry
Television networks face high financial risk when making programming decisions, often relying on limited historical data to forecast episodic viewership. This study introduces a machine learning framework that integrates natural language processing (NLP) features from over 25000 television episodes with traditional viewership data to enhance predictive accuracy. By extracting emotional tone, cognitive complexity, and narrative structure from episode dialogue, we evaluate forecasting performance…

Towards Efficient Speech-Text Jointly Decoding within One Speech Language Model
Haibin Wu, Yuxuan Hu, Ruchao Fan, Xiaofei Wang, Kenichi Kumatani, Bo Ren, Jianwei Yu, Heng Lu, Lijuan Wang, Yao Qian, Jinyu Li
https://arxiv.org/abs/2506.04518

Towards Efficient Speech-Text Jointly Decoding within One Speech Language Model
Speech language models (Speech LMs) enable end-to-end speech-text modelling within a single model, offering a promising direction for spoken dialogue systems. The choice of speech-text jointly decoding paradigm plays a critical role in performance, efficiency, and alignment quality. In this work, we systematically compare representative joint speech-text decoding strategies-including the interleaved, and parallel generation paradigms-under a controlled experimental setup using the same base lan…

Today I had cause to get out my old #Acorn #RISCOS 3 Style Guide to demonstrate that the fundamentals of good #UX can date back well over 30 years - same with the

Optimizing Conversational Product Recommendation via Reinforcement Learning
Kang Liu
https://arxiv.org/abs/2507.01060 https://arxiv.o…

Optimizing Conversational Product Recommendation via Reinforcement Learning
We propose a reinforcement learning-based approach to optimize conversational strategies for product recommendation across diverse industries. As organizations increasingly adopt intelligent agents to support sales and service operations, the effectiveness of a conversation hinges not only on what is recommended but how and when recommendations are delivered. We explore a methodology where agentic systems learn optimal dialogue policies through feedback-driven reinforcement learning. By mining …

Enhancing User Engagement in Socially-Driven Dialogue through Interactive LLM Alignments
Jiashuo Wang, Kaitao Song, Chunpu Xu, Changhe Song, Yang Xiao, Dongsheng Li, Lili Qiu, Wenjie Li
https://arxiv.org/abs/2506.21497

Enhancing User Engagement in Socially-Driven Dialogue through Interactive LLM Alignments
Enhancing user engagement through interactions plays an essential role in socially-driven dialogues. While prior works have optimized models to reason over relevant knowledge or plan a dialogue act flow, the relationship between user engagement and knowledge or dialogue acts is subtle and does not guarantee user engagement in socially-driven dialogues. To this end, we enable interactive LLMs to learn user engagement by leveraging signals from the future development of conversations. Specificall…

THE WASTIVE: An Interactive Ebb and Flow of Digital Fabrication Waste
Yifan Shan, Bo Liu, Sebastian Bidegain, Thijs Roumen
https://arxiv.org/abs/2505.21153

THE WASTIVE: An Interactive Ebb and Flow of Digital Fabrication Waste
What if digital fabrication waste could observe the world? What would they see? What would they say? "THE WASTIVE" reimagines digital fabrication waste as sentient observers, giving them a poetic voice through interactive art. As viewers approach, the installation awakens, mimicking the rhythmic ebb and flow of ocean waves - a silent dialogue where discarded materials "observe" and respond to human presence. These interactions echo the gentle murmurs of the sea, transforming technological resid…

Finished “You Are Here” by David Nicholls.
A mutual friend convinces Michael & Marnie to hike, at least partway, from coast to coast across the English countryside. Not intended for each other, initially, a sweet & genuine connection deepens with every step. So, too, does healing & growth in the aftermaths of failed marriages.
Great character development & fantastic dialogue. You LIKE them very much. Rushed ending, though.
4/5 stars ⭐️⭐️⭐️⭐️

You Are Here
Sometimes you need to get lost to find your way . . . …

RiOSWorld: Benchmarking the Risk of Multimodal Compter-Use Agents
Jingyi Yang, Shuai Shao, Dongrui Liu, Jing Shao
https://arxiv.org/abs/2506.00618 https://…

RiOSWorld: Benchmarking the Risk of Multimodal Compter-Use Agents
With the rapid development of multimodal large language models (MLLMs), they are increasingly deployed as autonomous computer-use agents capable of accomplishing complex computer tasks. However, a pressing issue arises: Can the safety risk principles designed and aligned for general MLLMs in dialogue scenarios be effectively transferred to real-world computer-use scenarios? Existing research on evaluating the safety risks of MLLM-based computer-use agents suffers from several limitations: it ei…

Modeling and Visualization Reasoning for Stakeholders in Education and Industry Integration Systems: Research on Structured Synthetic Dialogue Data Generation Based on NIST Standards
Wei Meng
https://arxiv.org/abs/2506.16952

Modeling and Visualization Reasoning for Stakeholders in Education and Industry Integration Systems: Research on Structured Synthetic Dialogue Data Generation Based on NIST Standards
This study addresses the structural complexity and semantic ambiguity in stakeholder interactions within the Education-Industry Integration (EII) system. The scarcity of real interview data, absence of structured variable modeling, and lack of interpretability in inference mechanisms have limited the analytical accuracy and policy responsiveness of EII research. To resolve these challenges, we propose a structural modeling paradigm based on the National Institute of Standards and Technology (NI…

Real-time Generation of Various Types of Nodding for Avatar Attentive Listening System
Kazushi Kato, Koji Inoue, Divesh Lala, Keiko Ochi, Tatsuya Kawahara
https://arxiv.org/abs/2507.23298

Real-time Generation of Various Types of Nodding for Avatar Attentive Listening System
In human dialogue, nonverbal information such as nodding and facial expressions is as crucial as verbal information, and spoken dialogue systems are also expected to express such nonverbal behaviors. We focus on nodding, which is critical in an attentive listening system, and propose a model that predicts both its timing and type in real time. The proposed model builds on the voice activity projection (VAP) model, which predicts voice activity from both listener and speaker audio. We extend it …

FD-Bench: A Full-Duplex Benchmarking Pipeline Designed for Full Duplex Spoken Dialogue Systems
Yizhou Peng, Yi-Wen Chao, Dianwen Ng, Yukun Ma, Chongjia Ni, Bin Ma, Eng Siong Chng
https://arxiv.org/abs/2507.19040

FD-Bench: A Full-Duplex Benchmarking Pipeline Designed for Full Duplex Spoken Dialogue Systems
Full-duplex spoken dialogue systems (FDSDS) enable more natural human-machine interactions by allowing real-time user interruptions and backchanneling, compared to traditional SDS that rely on turn-taking. However, existing benchmarks lack metrics for FD scenes, e.g., evaluating model performance during user interruptions. In this paper, we present a comprehensive FD benchmarking pipeline utilizing LLMs, TTS, and ASR to address this gap. It assesses FDSDS's ability to handle user interruptions,…

FACE: A Fine-grained Reference Free Evaluator for Conversational Recommender Systems
Hideaki Joko, Faegheh Hasibi
https://arxiv.org/abs/2506.00314 https://…

FACE: A Fine-grained Reference Free Evaluator for Conversational Recommender Systems
A systematic, reliable, and low-cost evaluation of Conversational Recommender Systems (CRSs) remains an open challenge. Existing automatic CRS evaluation methods are proven insufficient for evaluating the dynamic nature of recommendation conversations. This work proposes FACE: a Fine-grained, Aspect-based Conversation Evaluation method that provides evaluation scores for diverse turn and dialogue level qualities of recommendation conversations. FACE is reference-free and shows strong correlatio…

Series A, Episode 06 - Seek-Locate-Destroy
RAI: Yes, Supreme Commander.
SERVALAN: Let them know, too, that any lack of cooperation, any hesitation in responding to an order, will be treated as mutiny. Let them know I have said this. Dismissed. [Rai clicks his heels and exits. There is a bleep from the comm. Servalan ignores it, looking pensive. The comm bleeps again and Servalan reacts this time.]

Blakes7Bot | Search
Companion site to the Blakes7Bot Twitter, Mastodon, and Bluesky accounts. Automated lines of Blakes 7 dialog. Includes a script search facility.

What Can Robots Teach Us About Trust and Reliance? An interdisciplinary dialogue between Social Sciences and Social Robotics
Julien Wacquez (ETIS, CNRS), Elisabetta Zibetti (CHART), Joffrey Becker (ENSEA, ETIS), Lorenzo Aloe (ETIS, CHART), Fabio Amadio (LARSEN), Salvatore Anzalone (CHART), Lola Ca\~namero (ETIS, CY, CNRS, ENSEA), Serena Ivaldi (LARSEN, LORIA - AIS)

What Can Robots Teach Us About Trust and Reliance? An interdisciplinary dialogue between Social Sciences and Social Robotics
As robots find their way into more and more aspects of everyday life, questions around trust are becoming increasingly important. What does it mean to trust a robot? And how should we think about trust in relationships that involve both humans and non-human agents? While the field of Human-Robot Interaction (HRI) has made trust a central topic, the concept is often approached in fragmented ways. At the same time, established work in sociology, where trust has long been a key theme, is rarely br…

Transfinite Fixed Points in Alpay Algebra as Ordinal Game Equilibria in Dependent Type Theory
Faruk Alpay, Bugra Kilictas, Taylan Alpay
https://arxiv.org/abs/2507.19245 https://…

Transfinite Fixed Points in Alpay Algebra as Ordinal Game Equilibria in Dependent Type Theory
This paper contributes to the Alpay Algebra by demonstrating that the stable outcome of a self referential process, obtained by iterating a transformation through all ordinal stages, is identical to the unique equilibrium of an unbounded revision dialogue between a system and its environment. The analysis initially elucidates how classical fixed point theorems guarantee such convergence in finite settings and subsequently extends the argument to the transfinite domain, relying upon well founded…

Understanding User Preferences for Interaction Styles in Conversational Recommender Systems: The Predictive Role of System Qualities, User Experience, and Traits
Raj Mahmud, Shlomo Berkovsky, Mukesh Prasad, A. Baki Kocaballi
https://arxiv.org/abs/2508.02328

Understanding User Preferences for Interaction Styles in Conversational Recommender Systems: The Predictive Role of System Qualities, User Experience, and Traits
Conversational Recommender Systems (CRSs) deliver personalised recommendations through multi-turn natural language dialogue and increasingly support both task-oriented and exploratory interactions. Yet, the factors shaping user interaction preferences remain underexplored. In this within-subjects study (\(N = 139\)), participants experienced two scripted CRS dialogues, rated their experiences, and indicated the importance of eight system qualities. Logistic regression revealed that preference f…

Can Large Language Models Capture Human Risk Preferences? A Cross-Cultural Study
Bing Song, Jianing Liu, Sisi Jian, Chenyang Wu, Vinayak Dixit
https://arxiv.org/abs/2506.23107

Can Large Language Models Capture Human Risk Preferences? A Cross-Cultural Study
Large language models (LLMs) have made significant strides, extending their applications to dialogue systems, automated content creation, and domain-specific advisory tasks. However, as their use grows, concerns have emerged regarding their reliability in simulating complex decision-making behavior, such as risky decision-making, where a single choice can lead to multiple outcomes. This study investigates the ability of LLMs to simulate risky decision-making scenarios. We compare model-generate…

AC/DC: LLM-based Audio Comprehension via Dialogue Continuation
Yusuke Fujita, Tomoya Mizumoto, Atsushi Kojima, Lianbo Liu, Yui Sudo
https://arxiv.org/abs/2506.10312

AC/DC: LLM-based Audio Comprehension via Dialogue Continuation
We propose an instruction-following audio comprehension model that leverages the dialogue continuation ability of large language models (LLMs). Instead of directly generating target captions in training data, the proposed method trains a model to produce responses as if the input caption triggered a dialogue. This dialogue continuation training mitigates the caption variation problem. Learning to continue a dialogue effectively captures the caption's meaning beyond its surface-level words. As a…

AURA: Agent for Understanding, Reasoning, and Automated Tool Use in Voice-Driven Tasks
Leander Melroy Maben, Gayathri Ganesh Lakshmy, Srijith Radhakrishnan, Siddhant Arora, Shinji Watanabe
https://arxiv.org/abs/2506.23049

AURA: Agent for Understanding, Reasoning, and Automated Tool Use in Voice-Driven Tasks
Despite advances in language and speech technologies, no open-source system enables full speech-to-speech, multi-turn dialogue with integrated tool use and agentic reasoning. We introduce AURA (Agent for Understanding, Reasoning, and Automated Tool Use), the first open-source, speech-native assistant capable of completing complex, goal-driven tasks through dynamic tool invocation and multi-turn conversation. AURA combines open-weight ASR, TTS, and LLMs in a cascaded pipeline and supports tools …

Out-of-Context Abduction: LLMs Make Inferences About Procedural Data Leveraging Declarative Facts in Earlier Training Data
Sohaib Imran, Rob Lamb, Peter M. Atkinson
https://arxiv.org/abs/2508.00741

Out-of-Context Abduction: LLMs Make Inferences About Procedural Data Leveraging Declarative Facts in Earlier Training Data
Large language models (LLMs) are trained on large corpora, yet it is unclear whether they can reason about the information present within their training data. We design experiments to study out-of-context abduction in LLMs, the ability to infer the most plausible explanations for observations using relevant facts present in training data. We train treatment LLMs on names and behavior descriptions of fictitious chatbots, but not on examples of dialogue with the chatbots. We find that OpenAI's GP…

Feedstack: Layering Structured Representations over Unstructured Feedback to Scaffold Human AI Conversation
Hannah Vy Nguyen, Yu-Chun Grace Yen, Omar Shakir, Hang Huynh, Sebastian Gutierrez, June A. Smith, Sheila Jimenez, Salma Abdelgelil, Stephen MacNeil
https://arxiv.org/abs/2506.03052…

Feedstack: Layering Structured Representations over Unstructured Feedback to Scaffold Human AI Conversation
Many conversational user interfaces facilitate linear conversations with turn-based dialogue, similar to face-to-face conversations between people. However, digital conversations can afford more than simple back-and-forth; they can be layered with interaction techniques and structured representations that scaffold exploration, reflection, and shared understanding between users and AI systems. We introduce Feedstack, a speculative interface that augments feedback conversations with layered affor…

The Eloquence team submission for task 1 of MLC-SLM challenge
Lorenzo Concina, Jordi Luque, Alessio Brutti, Marco Matassoni, Yuchen Zhang
https://arxiv.org/abs/2507.19308 https:…

The Eloquence team submission for task 1 of MLC-SLM challenge
In this paper, we present our studies and experiments carried out for the task 1 of the Challenge and Workshop on Multilingual Conversational Speech Language Model (MLC-SLM), which focuses on advancing multilingual conversational speech recognition through the development of speech language models architectures. Given the increasing relevance of real-world conversational data for building robust Spoken Dialogue Systems, we explore three approaches to multilingual ASR. First, we conduct an evalu…

Towards Multimodal Social Conversations with Robots: Using Vision-Language Models
Ruben Janssens, Tony Belpaeme
https://arxiv.org/abs/2507.19196 https://ar…

Towards Multimodal Social Conversations with Robots: Using Vision-Language Models
Large language models have given social robots the ability to autonomously engage in open-domain conversations. However, they are still missing a fundamental social skill: making use of the multiple modalities that carry social interactions. While previous work has focused on task-oriented interactions that require referencing the environment or specific phenomena in social interactions such as dialogue breakdowns, we outline the overall needs of a multimodal system for social conversations wit…

Thinking in Character: Advancing Role-Playing Agents with Role-Aware Reasoning
Yihong Tang, Kehai Chen, Muyun Yang, Zhengyu Niu, Jing Li, Tiejun Zhao, Min Zhang
https://arxiv.org/abs/2506.01748

Thinking in Character: Advancing Role-Playing Agents with Role-Aware Reasoning
The advancement of Large Language Models (LLMs) has spurred significant interest in Role-Playing Agents (RPAs) for applications such as emotional companionship and virtual interaction. However, recent RPAs are often built on explicit dialogue data, lacking deep, human-like internal thought processes, resulting in superficial knowledge and style expression. While Large Reasoning Models (LRMs) can be employed to simulate character thought, their direct application is hindered by attention diversi…

AI Tutors vs. Tenacious Myths: Evidence from Personalised Dialogue Interventions in Education
Brooklyn J. Corbett, Jason M. Tangen
https://arxiv.org/abs/2506.09292

AI Tutors vs. Tenacious Myths: Evidence from Personalised Dialogue Interventions in Education
Misconceptions in psychology and education persist despite clear contradictory evidence, resisting traditional correction methods. This study investigated whether personalised AI dialogue could effectively correct these stubborn beliefs. In a preregistered experiment (N = 375), participants holding strong psychology misconceptions engaged in one of three interventions: (1) personalised AI dialogue targeting their specific misconception, (2) generic textbook-style refutation, or (3) neutral AI d…

The Thin Line Between Comprehension and Persuasion in LLMs
Adrian de Wynter, Tangming Yuan
https://arxiv.org/abs/2507.01936 https://a…

The Thin Line Between Comprehension and Persuasion in LLMs
Large language models (LLMs) are excellent at maintaining high-level, convincing dialogues. They are being fast deployed as chatbots and evaluators in sensitive areas, such as peer review and mental health applications. This, along with the disparate accounts on their reasoning capabilities, calls for a closer examination of LLMs and their comprehension of dialogue. In this work we begin by evaluating LLMs' ability to maintain a debate--one of the purest yet most complex forms of human communic…

Transordinal Fixed-Point Operators and Self-Referential Games: A Categorical Framework for Reflective Semantic Convergence
Faruk Alpay, Hamdi Al Alakkad
https://arxiv.org/abs/2507.16620

Transordinal Fixed-Point Operators and Self-Referential Games: A Categorical Framework for Reflective Semantic Convergence
We present a new theoretical framework that unifies category-theoretic fixed-point constructions, transfinite recursion, and game-based semantics to model how interpretations of language can stabilize through unlimited self-reference. By iterating a meaning-refinement operator across all ordinal stages, we isolate a unique "transordinal" fixed point and show, via a hierarchy of reflective games, that this same object is the sole equilibrium of an infinite dialogue between a text and its interpr…

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…

Approaching Dialogue State Tracking via Aligning Speech Encoders and LLMs
\v{S}imon Sedl\'a\v{c}ek, Bolaji Yusuf, J\'an \v{S}vec, Pradyoth Hegde, Santosh Kesiraju, Old\v{r}ich Plchot, Jan \v{C}ernock\'y
https://arxiv.org/abs/2506.08633

Approaching Dialogue State Tracking via Aligning Speech Encoders and LLMs
In this work, we approach spoken Dialogue State Tracking (DST) by bridging the representation spaces of speech encoders and LLMs via a small connector module, with a focus on fully open-sourced and open-data components (WavLM-large, OLMo). We focus on ablating different aspects of such systems including full/LoRA adapter fine-tuning, the effect of agent turns in the dialogue history, as well as fuzzy matching-based output post-processing, which greatly improves performance of our systems on nam…

DialogueForge: LLM Simulation of Human-Chatbot Dialogue
Ruizhe Zhu, Hao Zhu, Yaxuan Li, Syang Zhou, Shijing Cai, Malgorzata Lazuka, Elliott Ash
https://arxiv.org/abs/2507.15752

DialogueForge: LLM Simulation of Human-Chatbot Dialogue
Collecting human-chatbot dialogues typically demands substantial manual effort and is time-consuming, which limits and poses challenges for research on conversational AI. In this work, we propose DialogueForge - a framework for generating AI-simulated conversations in human-chatbot style. To initialize each generated conversation, DialogueForge uses seed prompts extracted from real human-chatbot interactions. We test a variety of LLMs to simulate the human chatbot user, ranging from state-of-th…

This https://arxiv.org/abs/2504.18410 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csHC_…

Can Code Outlove Blood? An LLM-based VR Experience to Prompt Reflection on Parental Verbal Abuse
Parental verbal abuse leaves lasting emotional impacts, yet current therapeutic approaches often lack immersive self-reflection opportunities. To address this, we developed a VR experience powered by LLMs to foster reflection on parental verbal abuse. Participants with relevant experiences engage in a dual-phase VR experience: first assuming the role of a verbally abusive parent, interacting with an LLM portraying a child, then observing the LLM reframing abusive dialogue into warm, supportive …

Modelling Adjectival Modification Effects on Semantic Plausibility
Anna Golub, Beate Zywietz, Annerose Eichel
https://arxiv.org/abs/2507.21828 https://arxi…

Modelling Adjectival Modification Effects on Semantic Plausibility
While the task of assessing the plausibility of events such as ''news is relevant'' has been addressed by a growing body of work, less attention has been paid to capturing changes in plausibility as triggered by event modification. Understanding changes in plausibility is relevant for tasks such as dialogue generation, commonsense reasoning, and hallucination detection as it allows to correctly model, for example, ''gentle sarcasm'' as a sign of closeness rather than unkindness among friends [9…

A Third Paradigm for LLM Evaluation: Dialogue Game-Based Evaluation using clembench
David Schlangen, Sherzod Hakimov, Jonathan Jordan, Philipp Sadler
https://arxiv.org/abs/2507.08491

A Third Paradigm for LLM Evaluation: Dialogue Game-Based Evaluation using clembench
There are currently two main paradigms for evaluating large language models (LLMs), reference-based evaluation and preference-based evaluation. The first, carried over from the evaluation of machine learning models in general, relies on pre-defined task instances, for which reference task executions are available. The second, best exemplified by the LM-arena, relies on (often self-selected) users bringing their own intents to a site that routes these to several models in parallel, among whose r…

Prompt-Guided Turn-Taking Prediction
Koji Inoue, Mikey Elmers, Yahui Fu, Zi Haur Pang, Divesh Lala, Keiko Ochi, Tatsuya Kawahara
https://arxiv.org/abs/2506.21191

Prompt-Guided Turn-Taking Prediction
Turn-taking prediction models are essential components in spoken dialogue systems and conversational robots. Recent approaches leverage transformer-based architectures to predict speech activity continuously and in real-time. In this study, we propose a novel model that enables turn-taking prediction to be dynamically controlled via textual prompts. This approach allows intuitive and explicit control through instructions such as "faster" or "calmer" adapting dynamically to conversational partne…

Domain Knowledge-Enhanced LLMs for Fraud and Concept Drift Detection
Ali \c{S}enol, Garima Agrawal, Huan Liu
https://arxiv.org/abs/2506.21443 https://arxiv.org/pdf/2506.21443 https://arxiv.org/html/2506.21443
arXiv:2506.21443v1 Announce Type: new
Abstract: Detecting deceptive conversations on dynamic platforms is increasingly difficult due to evolving language patterns and Concept Drift (CD)\-i.e., semantic or topical shifts that alter the context or intent of interactions over time. These shifts can obscure malicious intent or mimic normal dialogue, making accurate classification challenging. While Large Language Models (LLMs) show strong performance in natural language tasks, they often struggle with contextual ambiguity and hallucinations in risk\-sensitive scenarios. To address these challenges, we present a Domain Knowledge (DK)\-Enhanced LLM framework that integrates pretrained LLMs with structured, task\-specific insights to perform fraud and concept drift detection. The proposed architecture consists of three main components: (1) a DK\-LLM module to detect fake or deceptive conversations; (2) a drift detection unit (OCDD) to determine whether a semantic shift has occurred; and (3) a second DK\-LLM module to classify the drift as either benign or fraudulent. We first validate the value of domain knowledge using a fake review dataset and then apply our full framework to SEConvo, a multiturn dialogue dataset that includes various types of fraud and spam attacks. Results show that our system detects fake conversations with high accuracy and effectively classifies the nature of drift. Guided by structured prompts, the LLaMA\-based implementation achieves 98\% classification accuracy. Comparative studies against zero\-shot baselines demonstrate that incorporating domain knowledge and drift awareness significantly improves performance, interpretability, and robustness in high\-stakes NLP applications.
toXiv_bot_toot

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new/
[5/6]:
NTPP: Generative Speech Language Modeling for Dual-Channel Spoken Dialogue via Next-Token-Pair Pr...

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…

TAPS: Tool-Augmented Personalisation via Structured Tagging
Ekaterina Taktasheva, Jeff Dalton
https://arxiv.org/abs/2506.20409 https://

TAPS: Tool-Augmented Personalisation via Structured Tagging
Recent advancements in tool-augmented large language models have enabled them to interact with external tools, enhancing their ability to perform complex user tasks. However, existing approaches overlook the role of personalisation in guiding tool use. This work investigates how user preferences can be effectively integrated into goal-oriented dialogue agents. Through extensive analysis, we identify key weaknesses in the ability of LLMs to personalise tool use. To this end, we introduce \name, …

State-Inference-Based Prompting for Natural Language Trading with Game NPCs
Minkyung Kim, Junsik Kim, Hwidong Bae, Woongcheol Yang, Sangdon Park, Sohee Bae
https://arxiv.org/abs/2507.07203

State-Inference-Based Prompting for Natural Language Trading with Game NPCs
Large Language Models enable dynamic game interactions but struggle with rule-governed trading systems. Current implementations suffer from rule violations, such as item hallucinations and calculation errors, that erode player trust. Here, State-Inference-Based Prompting (SIBP) enables reliable trading through autonomous dialogue state inference and context-specific rule adherence. The approach decomposes trading into six states within a unified prompt framework, implementing context-aware item…

Can theory-driven learning analytics dashboard enhance human-AI collaboration in writing learning? Insights from an empirical experiment
Angxuan Chen, Jingjing Lian, Xinran Kuang, Jiyou Jia
https://arxiv.org/abs/2506.19364

Can theory-driven learning analytics dashboard enhance human-AI collaboration in writing learning? Insights from an empirical experiment
The integration of Generative AI (GenAI) into education has raised concerns about over-reliance and superficial learning, particularly in writing tasks in higher education. This study explores whether a theory-driven learning analytics dashboard (LAD) can enhance human-AI collaboration in the academic writing task by improving writing knowledge gains, fostering self-regulated learning (SRL) skills and building different human-AI dialogue characteristics. Grounded in Zimmerman's SRL framework, t…

Do We Talk to Robots Like Therapists, and Do They Respond Accordingly? Language Alignment in AI Emotional Support
Sophie Chiang, Guy Laban, Hatice Gunes
https://arxiv.org/abs/2506.16473

Do We Talk to Robots Like Therapists, and Do They Respond Accordingly? Language Alignment in AI Emotional Support
As conversational agents increasingly engage in emotionally supportive dialogue, it is important to understand how closely their interactions resemble those in traditional therapy settings. This study investigates whether the concerns shared with a robot align with those shared in human-to-human (H2H) therapy sessions, and whether robot responses semantically mirror those of human therapists. We analyzed two datasets: one of interactions between users and professional therapists (Hugging Face's…

ChatAR: Conversation Support using Large Language Model and Augmented Reality
Yuichiro Fujimoto
https://arxiv.org/abs/2506.16008 https://

ChatAR: Conversation Support using Large Language Model and Augmented Reality
Engaging in smooth conversations with others is a crucial social skill. However, differences in knowledge between conversation participants can sometimes hinder effective communication. To tackle this issue, this study proposes a real-time support system that integrates head-mounted display (HMD)-based augmented reality (AR) technology with large language models (LLMs). This system facilitates conversation by recognizing keywords during dialogue, generating relevant information using the LLM, r…

Finding Common Ground: Using Large Language Models to Detect Agreement in Multi-Agent Decision Conferences
Selina Heller, Mohamed Ibrahim, David Antony Selby, Sebastian Vollmer
https://arxiv.org/abs/2507.08440

Finding Common Ground: Using Large Language Models to Detect Agreement in Multi-Agent Decision Conferences
Decision conferences are structured, collaborative meetings that bring together experts from various fields to address complex issues and reach a consensus on recommendations for future actions or policies. These conferences often rely on facilitated discussions to ensure productive dialogue and collective agreement. Recently, Large Language Models (LLMs) have shown significant promise in simulating real-world scenarios, particularly through collaborative multi-agent systems that mimic group in…

Exploring Design of Multi-Agent LLM Dialogues for Research Ideation
Keisuke Ueda, Wataru Hirota, Takuto Asakura, Takahiro Omi, Kosuke Takahashi, Kosuke Arima, Tatsuya Ishigaki
https://arxiv.org/abs/2507.08350

Exploring Design of Multi-Agent LLM Dialogues for Research Ideation
Large language models (LLMs) are increasingly used to support creative tasks such as research idea generation. While recent work has shown that structured dialogues between LLMs can improve the novelty and feasibility of generated ideas, the optimal design of such interactions remains unclear. In this study, we conduct a comprehensive analysis of multi-agent LLM dialogues for scientific ideation. We compare different configurations of agent roles, number of agents, and dialogue depth to underst…

DocCHA: Towards LLM-Augmented Interactive Online diagnosis System
Xinyi Liu, Dachun Sun, Yi R. Fung, Dilek Hakkani-T\"ur, Tarek Abdelzaher
https://arxiv.org/abs/2507.07870

DocCHA: Towards LLM-Augmented Interactive Online diagnosis System
Despite the impressive capabilities of Large Language Models (LLMs), existing Conversational Health Agents (CHAs) remain static and brittle, incapable of adaptive multi-turn reasoning, symptom clarification, or transparent decision-making. This hinders their real-world applicability in clinical diagnosis, where iterative and structured dialogue is essential. We propose DocCHA, a confidence-aware, modular framework that emulates clinical reasoning by decomposing the diagnostic process into three…