paper-with-me

홈 › Papers

Analyzing the Effectiveness of the Underlying Reasoning Tasks in Multi-hop Question Answering

2023-02-12 · Xanh Ho, Anh-Khoa Duong Nguyen, Saku Sugawara, Akiko Aizawa

To explain the predicted answers and evaluate the reasoning abilities of models, several studies have utilized underlying reasoning (UR) tasks in multi-hop question answering (QA) datasets. However, it remains an open question as to how effective UR tasks are for the QA task when training models on both tasks in an end-to-end manner. In this study, we address this question by analyzing the effectiveness of UR tasks (including both sentence-level and entity-level tasks) in three aspects: (1) QA performance, (2) reasoning shortcuts, and (3) robustness. While the previous models have not been explicitly trained on an entity-level reasoning prediction task, we build a multi-task model that performs three tasks together: sentence-level supporting facts prediction, entity-level reasoning prediction, and answer prediction. Experimental results on 2WikiMultiHopQA and HotpotQA-small datasets reveal that (1) UR tasks can improve QA performance. Using four debiased datasets that are newly created, we demonstrate that (2) UR tasks are helpful in preventing reasoning shortcuts in the multi-hop QA task. However, we find that (3) UR tasks do not contribute to improving the robustness of the model on adversarial questions, such as sub-questions and inverted questions. We encourage future studies to investigate the effectiveness of entity-level reasoning in the form of natural language questions (e.g., sub-question forms).

📄 PDF Abstract BibTeX arXiv:2302.05963

Code (2)

alab-nii/multi-hop-analysis 공식 구현 pytorch
Alab-NII/2wikimultihop pytorch

Tasks

Multi-hop Question AnsweringOpen-Ended Question AnsweringPredictionQuestion AnsweringSentence

Similar Papers 제목 키워드 기반

ReJump: A Tree-Jump Representation for Analyzing and Improving LLM Reasoning

2025-11-30 · Yuchen Zeng, Shuibai Zhang, Wonjun Kang, Shutong Wu 외 arxiv

Large Reasoning Models (LRMs) are Large Language Models (LLMs) explicitly trained to generate long-form Chain-of-Thoughts (CoTs), achieving impressive success on challenging tasks like math and programming. However, thei…

Reinforcement Learning

Semantic Self-Consistency: Enhancing Language Model Reasoning via Semantic Weighting

2024-10-10 · Tim Knappe, Ryan Li, Ayush Chauhan, Kaylee Chhua 외

While large language models (LLMs) have rapidly improved their performance on a broad number of tasks, they still often fall short on reasoning tasks. As LLMs become more integrated in diverse real-world tasks, advancing…

Language ModelingLanguage Modelling

Algorithmic Thinking Theory

2025-12-04 · MohammadHossein Bateni, Vincent Cohen-Addad, Yuzhou Gu, Silvio Lattanzi 외 arxiv

Large language models (LLMs) have proven to be highly effective for solving complex reasoning tasks. Surprisingly, their capabilities can often be improved by iterating on previously generated solutions. In this context,…

From Perception to Reasoning: Deep Thinking Empowers Multimodal Large Language Models

2025-11-17 · Wenxin Zhu, Andong Chen, Yuchen Song, Kehai Chen 외 arxiv

With the remarkable success of Multimodal Large Language Models (MLLMs) in perception tasks, enhancing their complex reasoning capabilities has emerged as a critical research focus. Existing models still suffer from chal…

TempoGPT: Enhancing Temporal Reasoning via Quantizing Embedding

2025-01-13 · Haochuan Zhang, Chunhua Yang, Jie Han, Liyang Qin 외

Multi-modal language model has made advanced progress in vision and audio, but still faces significant challenges in dealing with complex reasoning tasks in the time series domain. The reasons are twofold. First, labels …

Language ModelingLanguage ModellingTime Series