A STEP towards Interpretable Multi-Hop Reasoning:Bridge Phrase Identification and Query Expansion
We propose an unsupervised method for the identification of bridge phrases in multi-hop question answering (QA). Our method constructs a graph of noun phrases from the question and the available context, and applies the Steiner tree algorithm to identify the minimal sub-graph that connects all question phrases. Nodes in the sub-graph that bridge loosely-connected or disjoint subsets of question phrases due to low-strength semantic relations are extracted as bridge phrases. The identified bridge phrases are then used to expand the query based on the initial question, helping in increasing the relevance of evidence that has little lexical overlap or semantic relation with the question. Through an evaluation on HotpotQA, a popular dataset for multi-hop QA, we show that our method yields: (a) improved evidence retrieval, (b) improved QA performance when using the retrieved sentences; and (c) effective and faithful explanations when answers are provided.
Code (0)
등록된 구현이 없습니다.
Tasks
Multi-hop Question AnsweringQuestion AnsweringRetrievalSimilar Papers 제목 키워드 기반
WISE: Weak-Supervision-Guided Step-by-Step Explanations for Multimodal LLMs in Image Classification
Multimodal Large Language Models (MLLMs) have shown promise in visual-textual reasoning, with Multimodal Chain-of-Thought (MCoT) prompting significantly enhancing interpretability. However, existing MCoT methods rely on …
Image ClassificationFrom <Answer> to <Think>: Multidimensional Supervision of Reasoning Process for LLM Optimization
Improving the multi-step reasoning ability of Large Language Models (LLMs) is a critical yet challenging task. The dominant paradigm, outcome-supervised reinforcement learning (RLVR), rewards only correct final answers, …
Reinforcement LearningQuestion AnsweringBridging the Gap Between Latent and Explicit Reasoning with Looped Transformers
Language models typically reason via explicit chain-of-thought (CoT), generating intermediate steps token-by-token. Latent CoT offers an alternative: it performs multi-step reasoning in the model's hidden states, replaci…
Enhancing Medical Visual Grounding via Knowledge-guided Spatial Prompts
Medical Visual Grounding (MVG) aims to identify diagnostically relevant phrases from free-text radiology reports and localize their corresponding regions in medical images, providing interpretable visual evidence to supp…
Multimodal ReasoningVisual GroundingAssessing the Bilingual Knowledge Learned by Neural Machine Translation Models
Machine translation (MT) systems translate text between different languages by automatically learning in-depth knowledge of bilingual lexicons, grammar and semantics from the training examples. Although neural machine tr…
Machine TranslationNMTTranslation