Main Conference - Day 3

The main conference takes place at Goodrich C. White Hall (WH). All oral sessions are are held at WH 208. All poster sessions are held in the WH main lobby. Blue names indicate the presenters.

Day 3 (August 5)

Start End Event
08:30 09:00 Registration
09:00 10:00 Keynote 3: Dilek Hakkani-Tür
10:00 10:30 Coffee Break
10:30 12:00 Oral Session 5
12:00 13:30 Lunch Break
13:30 15:00 Poster Session 3
15:00 15:30 Coffee break
15:30 16:00 Invited Talk
16:00 17:00 Awards & Closing Remarks

Oral Session 5

Papers

  1. MemeBuddy: Dialog-Style Audio Representations for Engaging Non-Visual Meme Experiences [paper] [slides]
    Chirag Bhansali, Vikas Ashok and Hae-Na Lee
  2. On the Structure of Address in Multi-Party Dialogue: From Discrete Labels to Continuous Levels [paper] [slides]
    Taiga Mori, Koji Inoue, Divesh Lala and Tatsuya Kawahara
  3. Bridging Talk and Thought: Understanding Dialogue Dynamics Across Collaborative Problem-Solving Contexts [paper] [slides]
    Zhengyuan Liu (Virtual), Stella Yin, Min-Yen Kan and Nancy Chen
  4. Seeing Is Not Sharing: Some Vision-Language Models Overestimate Common Ground in Asymmetric Dialogue [paper] [slides]
    Nan Li, Albert Gatt and Massimo Poesio
  5. CrossOracle: An Agentic Framework for Real-Time Expert Personas with Parallelized Acoustic Synthesis (Demo) [paper] [slides]
    Yash Raj Singh (Virtual)

Poster Session 3

  • Time: 13:30 – 15:00

Papers

  1. Evaluation of Paralinguistic-Aware Spoken Dialogue Systems using Next-Utterance Classification [paper] [poster]
    Kouki Miyazawa and Yoshinao Sato
  2. Better Scores, Worse Grounding: Hidden Regressions after Fine-Tuning in Dialogue Fact Verification [paper] [poster]
    Hyunkyung Park (Proxy: Nan Li) and Arkaitz Zubiaga
  3. LLMs and their Limited Theory of Mind: Evaluating Mental State Annotations in Situated Dialogue [paper] [poster]
    Katharine Kowalyshyn and Matthias Scheutz
  4. Enhancing Operational Safety via Agentic Dialogue Hazard Identification Analysis [paper] [poster]
    Sanjay Das, Ran Elgedawy, Ethan Seefried, Ryan Burchfield and Tirthankar Ghosal
  5. Building Task-Oriented Dialogue Systems via Instruction Guidance without Annotated Data [paper] [poster]
    Henry Gao and Jinho D. Choi
  6. Bounded Conversational Memory with Hybrid Retrieval and Evidence Highlighting for Multi-Session Dialogue Systems [paper] [poster]
    Manasa Mudunuri, Chandra Kiran Guntupalli, Mario Michael Kubek, Shiraj Pokharel and Murray Patterson
  7. Too Polite to Disagree: Understanding Sycophancy Propagation in Multi-Agent Systems [paper] [poster]
    Vira Kasprova, Amruta Parulekar, Abdulrahman AlRabah, Krishna Agaram, Ritwik Garg, Sagar Jha, Nimet Beyza Bozdag and Dilek Hakkani-Tur
  8. When the Database Fails: Prompting LLM Dialogue Agents for Safe Recovery in Task-Oriented Dialogue [paper] [poster]
    Mohammad Alijanpour Shalmani, Alale Rezvani Boroujeni and Jiann S. Yuan
  9. MTDiag: A Multi-Turn Diagnostic Dataset for Evaluating Clinical Reasoning in Large Language Models [paper] [poster]
    Pia Chouayfati (Proxy: Christoph Kowalski), Alexander M. Fichtl, Miriam Anschütz, George Doumat and Georg Groh
  10. PERSONAJUDGE: Simulating Individual Human Preference Judgments with Human-Centered Demonstration Data [paper] [poster]
    Zeyu He, Xuan Qi, Subramanian Chidambaram, Zhichao Xu, Vinayak Arannil, Lydia Chilton and Alex C. Williams
  11. Prior Lessons of Incremental Dialogue and Robot Action Management for the Age of Language Models (D&D) [paper] [poster]
    Casey Kennington (Proxy: Anna Manaseryan), Pierre Lison and David Schlangen
  12. Fractional Decay KV-Cache: Ownership-Aware Memory Management for Improved Inference Relevancy in Dialog Systems [paper] [poster]
    Sukanta Ganguly
  13. A Reinforcement Learning-Based Facilitator for Simulated Group Motivational Interviewing [paper] [poster]
    Alafate Abulimiti (Virtual), Vladislav Maraev, Agnès Helme-Guizon and Catherine Pelachaud