CSTree-SRI: Introspection-Driven Cognitive Semantic Tree for Multi-Turn Question Answering over Extra-Long Contexts

ACL ARR 2025 February Submission2979 Authors

Abstract: Large Language Models (LLMs) have achieved remarkable success in natural language processing (NLP), particularly in single-turn question answering (QA) on short-text. However, their performance significantly declines when applied to multi-turn QA over extra-long context (ELC), as they struggle to capture the logical correlations across multiple chunks of ELC and maintain the coherence of multi-turn Questions. To address the challenges, we propose the CSTree-SRI framework(Cognitive Semantic Tree through Summarization, Retrieval, and Introspection). CSTree-SRI dynamically constructs the CSTree to preserve logical coherence within ELC through hierarchical synthesis and introspective validation. Then a logic-driven traversal strategy on CSTree is designed to provide efficient information retrieval for question answering. Additionally, we construct a suite of multi-turn QA datasets and an evaluation benchmark tailored for ELC tasks, and comprehensive experiments demonstrate the framework's superiority in addressing the challenges of multi-turn QA over ELC.

Paper Type: Long

Research Area: Question Answering

Research Area Keywords: reading comprehension, logical reasoning, conversational QA, multi-turn QA, extra-long context QA

Contribution Types: NLP engineering experiment, Data resources

Languages Studied: python

Submission Number: 2979