Tootfinder

Exploring LLMs for Predicting Tutor Strategy and Student Outcomes in Dialogues
Fareya Ikram, Alexander Scarlatos, Andrew Lan
https://arxiv.org/abs/2507.06910

Exploring LLMs for Predicting Tutor Strategy and Student Outcomes in Dialogues
Tutoring dialogues have gained significant attention in recent years, given the prominence of online learning and the emerging tutoring abilities of artificial intelligence (AI) agents powered by large language models (LLMs). Recent studies have shown that the strategies used by tutors can have significant effects on student outcomes, necessitating methods to predict how tutors will behave and how their actions impact students. However, few works have studied predicting tutor strategy in dialog…

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…

ChatGPT on the Road: Leveraging Large Language Model-Powered In-vehicle Conversational Agents for Safer and More Enjoyable Driving Experience
Yeana Lee Bond (Computer Science, Virginia Tech, Blacksburg, Virginia, USA), Mungyeong Choe (Industrial and Systems Engineering, Virginia Tech, Blacksburg, Virginia, USA), Baker Kasim Hasan (Computer Science, Virginia Tech, Blacksburg, Virginia, USA), Arsh Siddiqui (Computer Science, Virginia Tech, Blacksburg, Virginia, USA), Myounghoon Jeon (Com…

ChatGPT on the Road: Leveraging Large Language Model-Powered In-vehicle Conversational Agents for Safer and More Enjoyable Driving Experience
Studies on in-vehicle conversational agents have traditionally relied on pre-scripted prompts or limited voice commands, constraining natural driver-agent interaction. To resolve this issue, the present study explored the potential of a ChatGPT-based in-vehicle agent capable of carrying continuous, multi-turn dialogues. Forty drivers participated in our experiment using a motion-based driving simulator, comparing three conditions (No agent, Pre-scripted agent, and ChatGPT-based agent) as a with…

Beyond Single Labels: Improving Conversational Recommendation through LLM-Powered Data Augmentation
Haozhe Xu, Xiaohua Wang, Changze Lv, Xiaoqing Zheng
https://arxiv.org/abs/2508.05657

Beyond Single Labels: Improving Conversational Recommendation through LLM-Powered Data Augmentation
Conversational recommender systems (CRSs) enhance recommendation quality by engaging users in multi-turn dialogues, capturing nuanced preferences through natural language interactions. However, these systems often face the false negative issue, where items that a user might like are incorrectly labeled as negative during training, leading to suboptimal recommendations.Expanding the label set through data augmentation presents an intuitive solution but faces the challenge of balancing two key as…

Too Human to Model:The Uncanny Valley of LLMs in Social Simulation -- When Generative Language Agents Misalign with Modelling Principles
Yongchao Zeng, Calum Brown, Mark Rounsevell
https://arxiv.org/abs/2507.06310

Too Human to Model:The Uncanny Valley of LLMs in Social Simulation -- When Generative Language Agents Misalign with Modelling Principles
Large language models (LLMs) have been increasingly used to build agents in social simulation because of their impressive abilities to generate fluent, contextually coherent dialogues. Such abilities can enhance the realism of models. However, the pursuit of realism is not necessarily compatible with the epistemic foundation of modelling. We argue that LLM agents, in many regards, are too human to model: they are too expressive, detailed and intractable to be consistent with the abstraction, si…

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…

Do language models accommodate their users? A study of linguistic convergence
Terra Blevins, Susanne Schmalwieser, Benjamin Roth
https://arxiv.org/abs/2508.03276 https://…

Do language models accommodate their users? A study of linguistic convergence
While large language models (LLMs) are generally considered proficient in generating language, how similar their language usage is to that of humans remains understudied. In this paper, we test whether models exhibit linguistic convergence, a core pragmatic element of human language communication, asking: do models adapt, or converge, to the linguistic patterns of their user? To answer this, we systematically compare model completions of exisiting dialogues to the original human responses acros…

Whispering Agents: An event-driven covert communication protocol for the Internet of Agents
Kaibo Huang, Yukun Wei, WanSheng Wu, Tianhua Zhang, Zhongliang Yang, Linna Zhou
https://arxiv.org/abs/2508.02188

Whispering Agents: An event-driven covert communication protocol for the Internet of Agents
The emergence of the Internet of Agents (IoA) introduces critical challenges for communication privacy in sensitive, high-stakes domains. While standard Agent-to-Agent (A2A) protocols secure message content, they are not designed to protect the act of communication itself, leaving agents vulnerable to surveillance and traffic analysis. We find that the rich, event-driven nature of agent dialogues provides a powerful, yet untapped, medium for covert communication. To harness this potential, we i…

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…

Emotions in the archives: study scoops international award https://www.nationalarchives.gov.uk/about/news/emotions-in-the-archives-study-scoops-international-award/

Emotions in the archives: study scoops international award - The National Archives
The editors of a ground-breaking new study about emotions and archives which includes work by a researcher at The National Archives has won a prestigious award. Archives and Emotions: International Dialogues across Past, Present and Future won the Waldo Gifford Leland Award for excellent writing and usefulness for archivists. The study examines the role emotions […]

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…

Collaborative Editable Model
Kaiwen Tang, Aitong Wu, Yao Lu, Guangda Sun
https://arxiv.org/abs/2506.14146 https://arxiv.org/pdf/2506.…

Collaborative Editable Model
Vertical-domain large language models (LLMs) play a crucial role in specialized scenarios such as finance, healthcare, and law; however, their training often relies on large-scale annotated data and substantial computational resources, impeding rapid development and continuous iteration. To address these challenges, we introduce the Collaborative Editable Model (CoEM), which constructs a candidate knowledge pool from user-contributed domain snippets, leverages interactive user-model dialogues c…

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 …

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…

iLearnRobot: An Interactive Learning-Based Multi-Modal Robot with Continuous Improvement
Kohou Wang, ZhaoXiang Liu, Lin Bai, Kun Fan, Xiang Liu, Huan Hu, Kai Wang, Shiguo Lian
https://arxiv.org/abs/2507.22896

iLearnRobot: An Interactive Learning-Based Multi-Modal Robot with Continuous Improvement
It is crucial that robots' performance can be improved after deployment, as they are inherently likely to encounter novel scenarios never seen before. This paper presents an innovative solution: an interactive learning-based robot system powered by a Multi-modal Large Language Model(MLLM). A key feature of our system is its ability to learn from natural dialogues with non-expert users. We also propose chain of question to clarify the exact intent of the question before providing an answer and 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…

MultiVox: Benchmarking Voice Assistants for Multimodal Interactions
Ramaneswaran Selvakumar, Ashish Seth, Nishit Anand, Utkarsh Tyagi, Sonal Kumar, Sreyan Ghosh, Dinesh Manocha
https://arxiv.org/abs/2507.10859

MultiVox: Benchmarking Voice Assistants for Multimodal Interactions
The rapid progress of Large Language Models (LLMs) has empowered omni models to act as voice assistants capable of understanding spoken dialogues. These models can process multimodal inputs beyond text, such as speech and visual data, enabling more context-aware interactions. However, current benchmarks fall short in comprehensively evaluating how well these models generate context-aware responses, particularly when it comes to implicitly understanding fine-grained speech characteristics, such …

BD at BEA 2025 Shared Task: MPNet Ensembles for Pedagogical Mistake Identification and Localization in AI Tutor Responses
Shadman Rohan, Ishita Sur Apan, Muhtasim Ibteda Shochcho, Md Fahim, Mohammad Ashfaq Ur Rahman, AKM Mahbubur Rahman, Amin Ahsan Ali
https://arxiv.org/abs/2506.01817

BD at BEA 2025 Shared Task: MPNet Ensembles for Pedagogical Mistake Identification and Localization in AI Tutor Responses
We present Team BD's submission to the BEA 2025 Shared Task on Pedagogical Ability Assessment of AI-powered Tutors, under Track 1 (Mistake Identification) and Track 2 (Mistake Location). Both tracks involve three-class classification of tutor responses in educational dialogues - determining if a tutor correctly recognizes a student's mistake (Track 1) and whether the tutor pinpoints the mistake's location (Track 2). Our system is built on MPNet, a Transformer-based language model that combines …

Findings of the BEA 2025 Shared Task on Pedagogical Ability Assessment of AI-powered Tutors
Ekaterina Kochmar, Kaushal Kumar Maurya, Kseniia Petukhova, KV Aditya Srivatsa, Ana\"is Tack, Justin Vasselli
https://arxiv.org/abs/2507.10579

Findings of the BEA 2025 Shared Task on Pedagogical Ability Assessment of AI-powered Tutors
This shared task has aimed to assess pedagogical abilities of AI tutors powered by large language models (LLMs), focusing on evaluating the quality of tutor responses aimed at student's mistake remediation within educational dialogues. The task consisted of five tracks designed to automatically evaluate the AI tutor's performance across key dimensions of mistake identification, precise location of the mistake, providing guidance, and feedback actionability, grounded in learning science principl…

A Literature Review on Simulation in Conversational Recommender Systems
Haoran Zhang, Xin Zhao, Jinze Chen, Junpeng Guo
https://arxiv.org/abs/2506.20291 ht…

A Literature Review on Simulation in Conversational Recommender Systems
Conversational Recommender Systems (CRSs) have garnered attention as a novel approach to delivering personalized recommendations through multi-turn dialogues. This review developed a taxonomy framework to systematically categorize relevant publications into four groups: dataset construction, algorithm design, system evaluation, and empirical studies, providing a comprehensive analysis of simulation methods in CRSs research. Our analysis reveals that simulation methods play a key role in tacklin…

Mitigating Trojanized Prompt Chains in Educational LLM Use Cases: Experimental Findings and Detection Tool Design
Richard M. Charles, James H. Curry, Richard B. Charles
https://arxiv.org/abs/2507.14207

Mitigating Trojanized Prompt Chains in Educational LLM Use Cases: Experimental Findings and Detection Tool Design
The integration of Large Language Models (LLMs) in K--12 education offers both transformative opportunities and emerging risks. This study explores how students may Trojanize prompts to elicit unsafe or unintended outputs from LLMs, bypassing established content moderation systems with safety guardrils. Through a systematic experiment involving simulated K--12 queries and multi-turn dialogues, we expose key vulnerabilities in GPT-3.5 and GPT-4. This paper presents our experimental design, detai…

Machine-Readable Ads: Accessibility and Trust Patterns for AI Web Agents interacting with Online Advertisements
Joel Nitu, Heidrun M\"uhle, Andreas St\"ockl
https://arxiv.org/abs/2507.12844

Machine-Readable Ads: Accessibility and Trust Patterns for AI Web Agents interacting with Online Advertisements
Autonomous multimodal language models are rapidly evolving into web agents that can browse, click, and purchase items on behalf of users, posing a threat to display advertising designed for human eyes. Yet little is known about how these agents interact with ads or which design principles ensure reliable engagement. To address this, we ran a controlled experiment using a faithful clone of the news site TT.com, seeded with diverse ads: static banners, GIFs, carousels, videos, cookie dialogues, a…

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…