English
Related papers

Related papers: Multi-Hop Knowledge Graph Reasoning with Reward Sh…

200 papers

Multi-modal multi-hop question answering involves answering a question by reasoning over multiple input sources from different modalities. Existing methods often retrieve evidences separately and then use a language model to generate an…

Computation and Language · Computer Science 2023-08-08 Qian Yang , Qian Chen , Wen Wang , Baotian Hu , Min Zhang

Multi-hop question answering (QA) requires reasoning over multiple documents to answer a complex question and provide interpretable supporting evidence. However, providing supporting evidence is not enough to demonstrate that a model has…

Computation and Language · Computer Science 2022-09-16 Zhenyun Deng , Yonghua Zhu , Yang Chen , Qianqian Qi , Michael Witbrock , Patricia Riddle

Reasoning paths are reliable information in knowledge graph completion (KGC) in which algorithms can find strong clues of the actual relation between entities. However, in real-world applications, it is difficult to guarantee that…

Information Retrieval · Computer Science 2025-10-08 Yanning Hou , Sihang Zhou , Ke Liang , Lingyuan Meng , Xiaoshu Chen , Ke Xu , Siwei Wang , Xinwang Liu , Jian Huang

Reward function is essential in reinforcement learning (RL), serving as the guiding signal to incentivize agents to solve given tasks, however, is also notoriously difficult to design. In many cases, only imperfect rewards are available,…

Machine Learning · Computer Science 2023-02-06 Jianxiong Li , Xiao Hu , Haoran Xu , Jingjing Liu , Xianyuan Zhan , Qing-Shan Jia , Ya-Qin Zhang

Large language models (LLMs) remain brittle on multi-hop question answering (MHQA), where answering requires combining evidence across documents through retrieval and reasoning. Iterative retrieval systems can fail by locking onto an early…

Artificial Intelligence · Computer Science 2026-04-01 Xingyu Li , Rongguang Wang , Yuying Wang , Mengqing Guo , Chenyang Li , Tao Sheng , Sujith Ravi , Dan Roth

Building compositional explanations requires models to combine two or more facts that, together, describe why the answer to a question is correct. Typically, these "multi-hop" explanations are evaluated relative to one (or a small number…

Computation and Language · Computer Science 2021-09-09 Peter Jansen , Kelly Smith , Dan Moreno , Huitzilin Ortiz

This paper proposes a group deliberation oriented multi-agent conversational model to address the limitations of single large language models in complex reasoning tasks. The model adopts a three-level role division architecture consisting…

Artificial Intelligence · Computer Science 2026-01-01 Zheyu Shi , Dong Qiu , Shanlong Yu

Reinforcement Learning from Verifiable Rewards (RLVR) has recently shown that large language models (LLMs) can develop their own reasoning without direct supervision. However, applications in the medical domain, specifically for question…

Machine Learning · Computer Science 2025-09-22 Mirza Farhan Bin Tarek , Rahmatollah Beheshti

No real-world reward function is perfect. Sensory errors and software bugs may result in RL agents observing higher (or lower) rewards than they should. For example, a reinforcement learning agent may prefer states where a sensory error…

Artificial Intelligence · Computer Science 2017-08-22 Tom Everitt , Victoria Krakovna , Laurent Orseau , Marcus Hutter , Shane Legg

Fusion-in-decoder (Fid) (Izacard and Grave, 2020) is a generative question answering (QA) model that leverages passage retrieval with a pre-trained transformer and pushed the state of the art on single-hop QA. However, the complexity of…

Computation and Language · Computer Science 2022-05-20 Semih Yavuz , Kazuma Hashimoto , Yingbo Zhou , Nitish Shirish Keskar , Caiming Xiong

Graph-based retrieval-augmented generation (RAG) methods, typically built on knowledge graphs (KGs) with binary relational facts, have shown promise in multi-hop open-domain QA. However, their rigid retrieval schemes and dense similarity…

Computation and Language · Computer Science 2026-02-17 Wen-Sheng Lien , Yu-Kai Chan , Hao-Lung Hsiao , Bo-Kai Ruan , Meng-Fen Chiang , Chien-An Chen , Yi-Ren Yeh , Hong-Han Shuai

Recent advances in large language models (LLMs) have significantly improved multi-hop question answering (QA) through direct Chain-of-Thought (CoT) reasoning. However, the irreversible nature of CoT leads to error accumulation, making it…

Artificial Intelligence · Computer Science 2025-05-30 Xinjie Zhao , Fan Gao , Xingyu Song , Yingjian Chen , Rui Yang , Yanran Fu , Yuyang Wang , Yusuke Iwasawa , Yutaka Matsuo , Irene Li

Transformer-based models have advanced the field of question answering, but multi-hop reasoning, where answers require combining evidence across multiple passages, remains difficult. This paper presents a comprehensive evaluation of…

Computer Vision and Pattern Recognition · Computer Science 2025-09-29 Zichen Zhang , Kunlong Zhang , Hongwei Ruan , Yiming Luo

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…

Computation and Language · Computer Science 2023-02-14 Xanh Ho , Anh-Khoa Duong Nguyen , Saku Sugawara , Akiko Aizawa

Reward shaping is effective in addressing the sparse-reward challenge in reinforcement learning (RL) by providing immediate feedback through auxiliary, informative rewards. Based on the reward shaping strategy, we propose a novel multi-task…

Machine Learning · Computer Science 2025-10-28 Haozhe Ma , Zhengding Luo , Thanh Vinh Vo , Kuankuan Sima , Tze-Yun Leong

Nowadays, Knowledge graphs (KGs) have been playing a pivotal role in AI-related applications. Despite the large sizes, existing KGs are far from complete and comprehensive. In order to continuously enrich KGs, automatic knowledge…

Computation and Language · Computer Science 2021-11-12 Zhao Zhang , Fuzhen Zhuang , Hengshu Zhu , Chao Li , Hui Xiong , Qing He , Yongjun Xu

We present S-Path-RAG, a semantic-aware shortest-path Retrieval-Augmented Generation framework designed to improve multi-hop question answering over large knowledge graphs. S-Path-RAG departs from one-shot, text-heavy retrieval by…

Computation and Language · Computer Science 2026-03-26 Rong Fu , Yemin Wang , Tianxiang Xu , Yongtai Liu , Weizhi Tang , Wangyu Wu , Xiaowen Ma , Simon Fong

Explaining the behaviour of intelligent agents learned by reinforcement learning (RL) to humans is challenging yet crucial due to their incomprehensible proprioceptive states, variational intermediate goals, and resultant unpredictability.…

Machine Learning · Computer Science 2023-11-07 Wenhao Lu , Xufeng Zhao , Sven Magg , Martin Gromniak , Mengdi Li , Stefan Wermter

Learning multi-hop reasoning has been a key challenge for reading comprehension models, leading to the design of datasets that explicitly focus on it. Ideally, a model should not be able to perform well on a multi-hop question answering…

Computation and Language · Computer Science 2019-04-30 Jifan Chen , Greg Durrett

Large language models (LLMs) demonstrate strong reasoning abilities when prompted to generate chain-of-thought (CoT) explanations alongside answers. However, previous research on evaluating LLMs has solely focused on answer accuracy,…

Computation and Language · Computer Science 2024-06-21 Minh-Vuong Nguyen , Linhao Luo , Fatemeh Shiri , Dinh Phung , Yuan-Fang Li , Thuy-Trang Vu , Gholamreza Haffari
‹ Prev 1 8 9 10 Next ›