# Multi-Step Reasoning Over Unstructured Text with Beam Dense Retrieval

Source: [Multi-Step Reasoning Over Unstructured Text with Beam Dense Retrieval](<https://www.sota2.com/research/paper/68fa69bd1e209131cea23e9c>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:07:38.441Z

Authors: Chen Zhao, Chenyan Xiong, Jordan Boyd-Graber, Hal Daum\\'e III

Published: 2021-04-13T01:16:48.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2104.05883>)

[PDF](<https://arxiv.org/pdf/2104.05883.pdf>)