作者位次 #2/3ACL 2026Poster· Natural Language Processing
Talking to a Know-It-All GPT or a Second-Guesser C laude? How Repair reveals distinct Multi-Turn Behavior in LLM s
Clara Lachenmaier · Hannah Bultmann · Sina Zarrieß
摘要
Repair, an important resource for resolving trouble in human–human conversation, remains underexplored in human–LLM interaction.In this study, we investigate how LLMs engage in the interactive process of repair in multi-turn dialogues around solvable and unsolvable math questions. We examine whet...