Conversational QA

QA: Question Answering

Follow this topic Ask about this topic

Latest papers

17 papers4 papers in the last four weeks, up 33% on the four weeks before. 0.0% of all new papers.

Not One Belief: Answer Payloads, Persistence, and Dissociated Confidence Signals in Conversational Question Answering
Oct 26, 2026Duc-Vinh TranConversational QA Belief Updating in LLMs
School of Information and Communication Technology, Hanoi University of Science and Technology, Hanoi, 100000, Vietnam.
Is Complex Agentic Memory Always Needed? Naive RAG Is Stronger Than We Thought
Oct 22, 2026Zhengye Bao, Shengtao Zhang, Haokai Zhang +3Conversational QA Memory Management for LLM Agents
Luo Lab Undergraduate Division (LUD), Xi’an Jiaotong University · Shanghai Jiao Tong University · Zhejiang University +1
Do Conversational Agents Need Explicit Memory? A Controlled Comparison with Raw-History Retrieval
Oct 17, 2026Yongjie Zhou, Shuai Wang, Bevan Koopman +1LLM Agent Memory Long-Term Conversational Memory
The University of Queensland, Brisbane, Australia · CSIRO · Google
Test-Time Memory Construction
Oct 9, 2026Zijun Wang, Yifan Ji, Haidong Xin +6Conversational QA Memory-Augmented Language Models
School of Computer Science and Engineering, Northeastern University, China · Department of Computer Science and Technology, Tsinghua University, China · Alibaba Group, China
Learning to Retrieve Missing Evidence for Long-Term Memory QA
Sep 29, 2026Yi-Xuan Deng, Yi Zhang, Wei Liu +2Long-Term Conversational Memory Evidence Retrieval
Tsinghua University
JustMem: Just-Enough Memory Access for Long-Term Conversations
Sep 17, 2026Guanhua Chen, Yanting Wang, Wenjing Zhi +1Conversational Memory Conversational QA
Beihang University
Where to Look and What to Use: Retrieve-Localize-Generate for Long-Term Conversational Memory Question Answering
Sep 7, 2026Yifan Wang, Xinkui Lin, Yongxiu Xu +9Graph Retrieval-Augmented Generation Persistent Memory for Language Models
University of Electronic Science and Technology of China, Chengdu, China 4State Key Laboratory of Internet Architecture, Tsinghua University, Beijing, China · Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China 3School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China · 5Independent Researcher
RuleMem: Active Rule Memory for Long-Term Conversational Agents
Sep 3, 2026Xingyuan Zeng, Zuohan Wu, Quanming Yao +5Conversational QA Question Answering
Sun Yat-sen University, Zhuhai, China · The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China · Tsinghua University, State Key Laboratory of Space Network and Communications, Beijing National Research Center for Information Science and Technology, Beijing, China +2
Entity-Memory Graph Retrieval Improves Evidence Coverage in Long-Conversation Question Answering
Aug 28, 2026Shumao SunConversational QA Evidence Retrieval
Tsinghua University
post-graph-rag: A PostgreSQL-Native Bi-Temporal Graph RAG Engine with Temporal Grounding at Synthesis
Aug 14, 2026Chandan RajahKG Construction Conversational QA
Independent Researcher
When Your Agent Opens the Chat App: Agent-Controlled Search over Raw Chat Logs Rivals Structured Memory
Aug 13, 2026Ruizhe Li, Licheng Zhang, Benfeng Xu +3Conversational Memory Agentic Search
University of Science and Technology of China · MetaStone Technology
NeSy-RAG: Neuro-Symbolic RAG for Explainable Question Answering
Aug 6, 2026Jonas Gann, Michael GertzRetrieval-Augmented Generation Conversational QA
Data Science Group, Heidelberg University, Germany
uva-irlab-conv at SemEval-2026 Task 8: Multi-Turn RAG with Learned Sparse Retrieval and Listwise Reranking
Jun 10, 2026Simon Lupart, Kidist Amde Mekonnen, Zahra Abbasiantaeb +1Retrieval-Augmented Generation Conversational QA
University of Amsterdam Amsterdam, The Netherlands
Clarify, Abstain or Answer? Strategising in Conversation with Belief-Augmented Generation
May 25, 2026Joris Baan, Wilker Aziz, Barbara Plank +1Clarification Question Generation Question Answering
University of Amsterdam · LMU Munich · European Commission, Joint Research Centre (JRC), Brussels
Clarification Is Not Enough: Post-Clarification Answering Remains the Bottleneck in Multi-Turn QA
May 24, 2026Jinyan Su, Jennifer HealeyQuestion Answering Preference Elicitation
1Cornell University · 2Adobe Research
EviMem: Evidence-Gap-Driven Iterative Retrieval for Long-Term Conversational Memory
Apr 30, 2026Yuyang Li, Yime He, Zeyu Zhang +1Temporal IR Evidence Retrieval
The Australian National University · UNSW Sydney
EverydayGPT: Confidence-Gated Routing for Efficient and Safe Hybrid GPT-RAG Conversational QA
Apr 24, 2026Jaspreet Singh NahalLLM Inference Efficiency Retrieval-Augmented Generation
B.Tech Computer Science Engineering (Artificial Intelligence) Dr. A.P.J. Abdul Kalam Technical University, Delhi, India

Oct 26, 2026J/K move · Enter open · S save

Not One Belief: Answer Payloads, Persistence, and Dissociated Confidence Signals in Conversational Question Answering

Duc-Vinh Tran

School of Information and Communication Technology, Hanoi University of Science and Technology, Hanoi, 100000, Vietnam.

Conversational QA Belief Updating in LLMs Confidence Estimation in Language Models

Open paper AskPDF arXiv

Conversational QA systems should fix errors when users push back and signal which answers to trust. We split each follow-up into its speech act (re-ask, agree, or challenge) and its payload (an answer string, correct or not), and measure four confidence signals on the same transcripts: verbalized confidence, length-normalized likelihood, a frozen hidden-state probe, and P(True). Answers change when the user supplies an answer string and almost never under the speech act alone: in every retained full-size cell, the correct answer converts at least four times as many wrong answers as re-asking or agreement. The four signals disagree. On Qwen2.5-7B the frozen probe rises with answer persistence rather than truth; this holds on held-out questions, with Llama-3-8B (cleaned answers) as support, but not on four other models. Among 81 Qwen2.5-7B errors that survive one re-ask, re-asking, a fresh chat, or abstain repair almost none, while a gold answer repairs 75-95%. In two preregistered replications, every repair rate without an answer string stays below 0.15; a larger post-hoc rerun excludes 0.15 except for the empty elicit. With BM25 TriviaQA evidence, sentences that contain the answer repair 67-76% of persistent errors versus at most 12% when they do not. An end-to-end contain-gate cuts harm on TriviaQA, but a deployable gate that does not know the gold answer repairs few errors.