GPT-3.5 with chain-of-thought prompting still fails often on multi-hop reasoning with external knowledge, especially with distractors, counterfactual facts, non-sequential proof structures, and higher hop counts.
Multi-Step Reasoning Over Unstructured Text with Beam Dense Retrieval
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
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.
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Large Language Models Still Face Challenges in Multi-Hop Reasoning with External Knowledge
GPT-3.5 with chain-of-thought prompting still fails often on multi-hop reasoning with external knowledge, especially with distractors, counterfactual facts, non-sequential proof structures, and higher hop counts.