An Empirical Analysis of Multiple-Turn Reasoning Strategies in Reading Comprehension Tasks
Reading comprehension (RC) is a challenging task that requires synthesis of information across sentences and multiple turns of reasoning. Using a state-of-the-art RC model, we empirically investigate the performance of single-turn and multiple-turn reasoning on the SQuAD and MS MARCO datasets. The RC model is an end-to-end neural network with iterative attention, and uses reinforcement learning to dynamically control the number of turns. We find that multiple-turn reasoning outperforms single-turn reasoning for all question and answer types; further, we observe that enabling a flexible number of turns generally improves upon a fixed multiple-turn strategy. %across all question types, and is particularly beneficial to questions with lengthy, descriptive answers. We achieve results competitive to the state-of-the-art on these two datasets.
Code (0)
등록된 구현이 없습니다.
Tasks
DescriptiveReading ComprehensionReinforcement LearningReinforcement Learning (RL)Similar Papers 제목 키워드 기반
Modeling Multiple Support Strategies within a Single Turn for Emotional Support Conversations
Emotional Support Conversation (ESC) aims to assist individuals experiencing distress by generating empathetic and supportive dialogue. While prior work typically assumes that each supporter turn corresponds to a single …
Reinforcement LearningMulti-Turn Jailbreaks Are Simpler Than They Seem
While defenses against single-turn jailbreak attacks on Large Language Models (LLMs) have improved significantly, multi-turn jailbreaks remain a persistent vulnerability, often achieving success rates exceeding 70% again…
What Makes Large Language Models Reason in (Multi-Turn) Code Generation?
Prompting techniques such as chain-of-thought have established themselves as a popular vehicle for improving the outputs of large language models (LLMs). For code generation, however, their exact mechanics and efficacy a…
Code GenerationMulti-turn Training with Basic Human Feedback Helps Little on LLM Reasoning
The reasoning capabilities of Large Language Models (LLMs) are typically developed through the single-turn reinforcement learning, whereas real-world applications often involve multi-turn interactions with human feedback…
Reinforcement LearningQuantum and Classical Machine Learning in Decentralized Finance: Comparative Evidence from Multi-Asset Backtesting of Automated Market Makers
This study presents a comprehensive empirical comparison between quantum machine learning (QML) and classical machine learning (CML) approaches in Automated Market Makers (AMM) and Decentralized Finance (DeFi) trading st…
Quantum Machine Learning