Locate Then Ask: Interpretable Stepwise Reasoning for Multi-hop Question Answering
Multi-hop reasoning requires aggregating multiple documents to answer a complex question. Existing methods usually decompose the multi-hop question into simpler single-hop questions to solve the problem for illustrating the explainable reasoning process. However, they ignore grounding on the supporting facts of each reasoning step, which tends to generate inaccurate decompositions. In this paper, we propose an interpretable stepwise reasoning framework to incorporate both single-hop supporting sentence identification and single-hop question generation at each intermediate step, and utilize the inference of the current hop for the next until reasoning out the final result. We employ a unified reader model for both intermediate hop reasoning and final hop inference and adopt joint optimization for more accurate and robust multi-hop reasoning. We conduct experiments on two benchmark datasets HotpotQA and 2WikiMultiHopQA. The results show that our method can effectively boost performance and also yields a better interpretable reasoning process without decomposition supervision.
Code (1)
Tasks
Multi-hop Question AnsweringQuestion AnsweringQuestion GenerationQuestion-GenerationSentenceSimilar Papers 제목 키워드 기반
CausalStep: A Benchmark for Explicit Stepwise Causal Reasoning in Videos
Recent advances in large language models (LLMs) have improved reasoning in text and image domains, yet achieving robust video reasoning remains a significant challenge. Existing video benchmarks mainly assess shallow und…
Dynamic Graph Attention for Referring Expression Comprehension
Referring expression comprehension aims to locate the object instance described by a natural language referring expression in an image. This task is compositional and inherently requires visual reasoning on top of the re…
Graph AttentionReferring ExpressionReferring Expression ComprehensionVisual ReasoningBottom-Up Shift and Reasoning for Referring Image Segmentation
Referring image segmentation aims to segment the referent that is the corresponding object or stuff referred by a natural language expression in an image. Its main challenge lies in how to effectively and efficiently…
Image SegmentationSegmentationSemantic SegmentationVisual ReasoningStepPRM-RTL: Stepwise Process-Reward Guided LLM Fine-Tuning for Enhanced RTL Synthesis
Automatic generation of RTL code for digital hardware designs remains challenging due to long-horizon reasoning, multi-step dependencies, and strict correctness constraints in Verilog and VHDL. We present StepPRM-RTL, a …
Trajectory ModelingCode GenerationStepwise Think-Critique: A Unified Framework for Robust and Interpretable LLM Reasoning
Human beings solve complex problems through critical thinking, where reasoning and evaluation are intertwined to converge toward correct solutions. However, most existing large language models (LLMs) treat the reasoning …
Reinforcement LearningMathematical Reasoning