| Time |
Paper Title |
Authors |
| 9:55-10:05 |
Offline RLHF Methods Need More Accurate Supervision Signals |
Shiqi Wang, Zhengze Zhang, Wang Xiaoliang, Rui Zhao, Fei Tan and Nguyen, Cam-Tu |
| 10:05-10:15 |
Parameter-Efficient Detoxification with Contrastive Decoding |
Tong Niu, Caiming Xiong, Yingbo Zhou and Semih Yavuz |
| 10:15-10:25 |
Learning from Teaching Assistants to Formulate Subgoals for Programming Tasks: Exploring the Potential for AI Teaching Assistants |
Changyoon Lee, Junho Myung, Jieun Han, Jiho Jin and Alice Oh |
| 10:25-10:30 |
DOSA: A Dataset of Social Artifacts from Different Indian Geographical Subcultures |
Agrima Seth, Sanchit Ahuja, Kalika Bali and Sunayana Sitaram |
| Time |
Paper Title |
Authors |
| 11:45-13:45 |
To What Extent Are Large Language Models Capable of Generating Substantial Reflections for Motivational Interviewing Counseling Chatbots? A Human Evaluation |
Erkan Basar, Iris Hendrickx, Emiel Krahmer, Gert-Jan de Bruijn and Tibor Bosse |
| Exploring Human-AI Interaction: A Case Study on the Diplomacy Game |
Shumin Deng, Jintian Zhang, Ningyu Zhang and Bryan Hooi |
| Vision-Language Models under Cultural and Inclusive Considerations |
Antonia Karamolegkou, Phillip Rust, Ruixiang Cui, Yong Cao, Anders Søgaard and Daniel Hershcovich |
| Reference-free Medical Multi-document Summary Evaluation Metric via Contrastive Learning |
Jimin Lee and Hwanhee Lee |
| Aligning to Adults Is Easy, Aligning to Children Is Hard: A Study of Linguistic Alignment in Dialogue Systems |
Dorothea French, Sidney D’Mello and Katharina Von Der Wense |
| Direct Preference Optimization with an Offset |
Afra Amini, Tim Vieira and Ryan Cotterell |
| Book2Dial: Generating Teacher Student Interactions from Textbooks for Cost-Effective Development of Educational Chatbots |
Junling Wang, Jakub Macina, Nico Daheim, Sankalan Pal Chowdhury and Mrinmaya Sachan |
| My Answer is C: First-Token Probabilities Do Not Match Text Answers in Instruction-Tuned Language Models |
Xinpeng Wang, Bolei Ma, Chengzhi Hu, Leon Weber-Genzel, Paul Rottger, Frauke Kreuter, Dirk Hovy and Barbara Plank |
| Learning from Teaching Assistants to Formulate Subgoals for Programming Tasks: Exploring the Potential for AI Teaching Assistants |
Changyoon Lee, Junho Myung, Jieun Han, Jiho Jin and Alice Oh |
| Offline RLHF Methods Need More Accurate Supervision Signals |
Shiqi Wang, Zhengze Zhang, Wang Xiaoliang, Rui Zhao, Fei Tan and Nguyen, Cam-Tu |
| Time |
Paper Title |
Authors |
| 14:15-14:25 |
Human-Centered Design Recommendations for LLM-as-a-judge |
Qian Pan, Zahra Ashktorab, Michael Desmond, Martín Santillán Cooper, James M. Johnson, Rahul Nair, Elizabeth M. Daly and Werner Geyer |
| 14:25-14:35 |
Evaluating Large Language Models on Social Signal Sensitivity: An Appraisal Theory Approach |
Zhen Wu, Ritam Dutt and Carolyn Rose |
| 14:35-14:45 |
Evaluating Large Language Model Biases in Persona-Steered Generation |
Andy Liu, Mona Diab and Daniel Fried |
| 14:45-14:55 |
Human Speech Perception in Noise: Can Large Language Models Paraphrase to Improve It? |
Anupama Chingacham, Miaoran Zhang, Vera Demberg and Dietrich Klakow |