Multi-Step Reasoning Over Unstructured Text with Beam Dense Retrieval
Complex question answering often requires finding a reasoning chain that consists of multiple evidence pieces. Current approaches incorporate the strengths of structured knowledge and unstructured text, assuming text corpora is semi-structured. Building on dense retrieval methods, we propose a new multi-step retrieval approach (BeamDR) that iteratively forms an evidence chain through beam search in dense representations. When evaluated on multi-hop question answering, BeamDR is competitive to state-of-the-art systems, without using any semi-structured information. Through query composition in dense space, BeamDR captures the implicit relationships between evidence in the reasoning chain. The code is available at https://github.com/ henryzhao5852/BeamDR.
Code (1)
Tasks
Multi-hop Question AnsweringQuestion AnsweringRetrievalSimilar Papers 제목 키워드 기반
KG-GPT: A General Framework for Reasoning on Knowledge Graphs Using Large Language Models
While large language models (LLMs) have made considerable advancements in understanding and generating unstructured text, their application in structured data remains underexplored. Particularly, using LLMs for complex r…
Fact VerificationKnowledge GraphsRetrievalSentence+1BlendSQL: A Scalable Dialect for Unifying Hybrid Question Answering in Relational Algebra
Many existing end-to-end systems for hybrid question answering tasks can often be boiled down to a "prompt-and-pray" paradigm, where the user has limited control and insight into the intermediate reasoning steps used to …
Question AnsweringNatural Language Reasoning, A Survey
This survey paper proposes a clearer view of natural language reasoning in the field of Natural Language Processing (NLP), both conceptually and practically. Conceptually, we provide a distinct definition for natural lan…
Logical ReasoningMathematical ReasoningMulti-hop Question AnsweringNatural Language Inference+3VQA-GNN: Reasoning with Multimodal Knowledge via Graph Neural Networks for Visual Question Answering
Visual question answering (VQA) requires systems to perform concept-level reasoning by unifying unstructured (e.g., the context in question and answer; "QA context") and structured (e.g., knowledge graph for the QA conte…
Knowledge GraphsQuestion AnsweringVisual Question AnsweringVisual Question Answering (VQA)Structure Guided Prompt: Instructing Large Language Model in Multi-Step Reasoning by Exploring Graph Structure of the Text
Although Large Language Models (LLMs) excel at addressing straightforward reasoning tasks, they frequently struggle with difficulties when confronted by more complex multi-step reasoning due to a range of factors. Firstl…
Language ModelingLanguage ModellingLarge Language ModelNavigate