paper-with-me

Papers

No Answer is Better Than Wrong Answer: A Reflection Model for Document Level Machine Reading Comprehension

2020-09-25 · Findings of the Association for Computational Linguistics 2020 · Xuguang Wang, Linjun Shou, Ming Gong, Nan Duan, Daxin Jiang

The Natural Questions (NQ) benchmark set brings new challenges to Machine Reading Comprehension: the answers are not only at different levels of granularity (long and short), but also of richer types (including no-answer, yes/no, single-span and multi-span). In this paper, we target at this challenge and handle all answer types systematically. In particular, we propose a novel approach called Reflection Net which leverages a two-step training procedure to identify the no-answer and wrong-answer cases. Extensive experiments are conducted to verify the effectiveness of our approach. At the time of paper writing (May.~20,~2020), our approach achieved the top 1 on both long and short answer leaderboard, with F1 scores of 77.2 and 64.1, respectively.

📄 PDF Abstract BibTeX arXiv:2009.12056

Code (0)

등록된 구현이 없습니다.

Tasks

Machine Reading ComprehensionNatural QuestionsReading Comprehension

Similar Papers 제목 키워드 기반

First Try Matters: Revisiting the Role of Reflection in Reasoning Models

2025-10-09 · Liwei Kang, Yue Deng, Yao Xiao, Zhanfeng Mo 외 arxiv

Large language models have recently demonstrated significant gains in reasoning ability, often attributed to their capacity to generate longer chains of thought and engage in reflective reasoning. However, the contributi…

MAR:Multi-Agent Reflexion Improves Reasoning Abilities in LLMs

2025-12-23 · Onat Ozer, Yuchen Wang, Grace Wu, Daniel Dosti 외 arxiv

LLMs have shown the capacity to improve their performance on reasoning tasks through reflecting on their mistakes, and acting with these reflections in mind. However, continual reflections of the same LLM onto itself exh…

Question Answering

Wrong but Useful: Trajectory Value Beyond Answer Correctness in Multi-Agent Messages

2026-08-14 · Chih-Hsuan Yang, Anjir Ahmed Chowdhury, Cheng-Hau Yang, Weijian Zheng 외 arxiv

Multi-agent reasoning systems often use agreement, confidence, or automated scores to decide which messages should shape a final answer. Such filtering assumes that a message likely to be correct is also worth keeping. Y…

Easier to Mislead Than to Correct: Harmful and Beneficial Revision in LLM Conformity

2026-06-01 · Jiaming Qu, Lucheng Fu, Yibo Hu arxiv

Large language models are increasingly used in multi-agent systems, where they see and respond to other agents' answers. A key risk is conformity: a model may abandon its own answer simply because others agree on a diffe…

LLMs can implicitly learn from mistakes in-context

2025-02-12 · Lisa Alazraki, Maximilian Mozes, Jon Ander Campos, Yi Chern Tan 외

Learning from mistakes is a fundamental feature of human intelligence. Previous work has shown that Large Language Models (LLMs) can also learn from incorrect answers when provided with a comprehensive rationale detailin…

Mathematical Reasoning