Understanding Common Ground Misalignment in Goal-Oriented Dialog: A Case-Study with Ubuntu Chat Logs
Rupak Sarkar, Neha Srikanth, Taylor Pellegrin, Rachel Rudinger, Claire Bonial, Philip Resnik
摘要
While it is commonly accepted that maintaining common ground plays a role in conversational success, little prior research exists connecting conversational grounding to success in task-oriented conversations. We study failures of grounding in the Ubuntu IRC dataset, where participants use text-only communication to resolve technical issues. We find that disruptions in conversational flow often stem from a misalignment in common ground, driven by a divergence in beliefs and assumptions held by participants. These disruptions, which we call conversational friction, significantly correlate with task success. We find that although LLMs can identify overt cases of conversational friction, they struggle with subtler and more context-dependent instances requiring pragmatic or domain-specific reasoning.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper1
问问它们各自怎么用它它引用的顶会 Paper4
- MindCraft: Theory of Mind Modeling for Situated Dialogue in Collaborative TasksCristian-Paul Bara, Sky CH-Wang, Joyce ChaiEMNLP 2021 · 被引用 28 次
- Navigating Rifts in Human-LLM Grounding: Study and BenchmarkOmar Shaikh, Hussein Mozannar, Gagan Bansal, Adam Fourney 等ACL 2025 · 被引用 21 次
- Natural Language Decompositions of Implicit Content Enable Better Text RepresentationsAlexander Miserlis Hoyle, Rupak Sarkar, Pranav Goel, Philip ResnikEMNLP 2023 · 被引用 3 次
- Analyzing LLM Behavior in Dialogue Summarization: Unveiling Circumstantial Hallucination TrendsSanjana Ramprasad, Elisa Ferracane, Zachary C. LiptonACL 2024
相关 Paper
- Evaluating the Effectiveness of Large Language Models in Establishing Conversational GroundingBiswesh Mohapatra, Manav Nitin Kapadnis, Laurent Romary, Justine CassellEMNLP 2024 · 被引用 1 次
- An Annotated Corpus of Reference Resolution for Interpreting Common GroundingTakuma Udagawa, Akiko AizawaAAAI 2020 · 被引用 10 次
- Can LLMs Ground when they (Don't) Know: A Study on Direct and Loaded Political QuestionsClara Lachenmaier, Judith Sieker, Sina ZarrießACL 2025
- End-to-End Deep Reinforcement Learning for Conversation DisentanglementKaran Bhukar, Harshit Kumar, Dinesh Raghu, Ajay GuptaAAAI 2023 · 被引用 3 次
- Online Conversation Disentanglement with Pointer NetworksTao Yu, Shafiq R. JotyEMNLP 2020 · 被引用 2 次
