# Triggering Multi-Hop Reasoning for Question Answering in Language Models using Soft Prompts and Random Walks Source: [Triggering Multi-Hop Reasoning for Question Answering in Language Models using Soft Prompts and Random Walks]() Collection index: [llms.txt]() Data updated: 2026-01-04T04:29:53.197Z Authors: Kanishka Misra, Cicero Nogueira dos Santos, Siamak Shakeri Published: 2023-06-06T20:45:18.000Z ## Abstract Despite readily memorizing world knowledge about entities, pre-trained language models (LMs) struggle to compose together two or more facts to perform multi-hop reasoning in question-answering tasks. In this work, we propose techniques that improve upon this limitation by relying on random walks over structured knowledge graphs. Specifically, we use soft prompts to guide LMs to chain together their encoded knowledge by learning to map multi-hop questions to random walk paths that lead to the answer. Applying our methods on two T5 LMs shows substantial improvements over standard tuning approaches in answering questions that require 2-hop reasoning. ## 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. - [Multi-hop Question Answering on 2WikiMultiHopQA (test)](): Multi-hop Question Answering; 2WikiMultiHopQA (test); EM: 29.37. ## Original sources and implementation [Original paper]() [PDF]()