Related papers: Locate Then Ask: Interpretable Stepwise Reasoning …
Question answering (QA) over tables and text has gained much popularity over the years. Multi-hop table-text QA requires multiple hops between the table and text, making it a challenging QA task. Although several works have attempted to…
Multi-modal multi-hop question answering involves answering a question by reasoning over multiple input sources from different modalities. Existing methods often retrieve evidences separately and then use a language model to generate an…
Multi-hop retrieval-augmented generation (RAG) is a promising strategy for complex reasoning, yet existing iterative prompting approaches remain inefficient. They often regenerate predictable token sequences at every step and rely on…
Has there been real progress in multi-hop question-answering? Models often exploit dataset artifacts to produce correct answers, without connecting information across multiple supporting facts. This limits our ability to measure true…
Retrieving information from correlative paragraphs or documents to answer open-domain multi-hop questions is very challenging. To deal with this challenge, most of the existing works consider paragraphs as nodes in a graph and propose…
Step-by-step reasoning is widely used to enhance the reasoning ability of large language models (LLMs) in complex problems. Evaluating the quality of reasoning traces is crucial for understanding and improving LLM reasoning. However,…
Multi-hop reasoning is an effective approach for query answering (QA) over incomplete knowledge graphs (KGs). The problem can be formulated in a reinforcement learning (RL) setup, where a policy-based agent sequentially extends its…
The success of deep learning models on multi-hop fact verification has prompted researchers to understand the behavior behind their veracity. One possible way is erasure search: obtaining the rationale by entirely removing a subset of input…
Recent advancements in long-context modeling have enhanced language models (LMs) for complex tasks across multiple NLP applications. Despite this progress, we find that these models struggle with multi-hop reasoning and exhibit decreased…
Few-shot prompting is a surprisingly powerful way to use Large Language Models (LLMs) to solve various tasks. However, this approach struggles as the task complexity increases or when the individual reasoning steps of the task themselves…
Building compositional explanations requires models to combine two or more facts that, together, describe why the answer to a question is correct. Typically, these "multi-hop" explanations are evaluated relative to one (or a small number…
Multi-hop reasoning (MHR) is a process in artificial intelligence and natural language processing where a system needs to make multiple inferential steps to arrive at a conclusion or answer. In the context of knowledge graphs or databases,…
While large language models (LLMs) have demonstrated strong capabilities in tasks like question answering and fact verification, they continue to suffer from hallucinations and reasoning errors, especially in multi-hop tasks that require…
Multi-hop Question Answering (MHQA) adds layers of complexity to question answering, making it more challenging. When Language Models (LMs) are prompted with multiple search results, they are tasked not only with retrieving relevant…
We introduce a novel retrieval-augmented generation (RAG) framework tailored for multihop question answering. First, our system uses large language model (LLM) to decompose complex multihop questions into a sequence of single-hop…
Multi-hop question answering faces substantial challenges due to data sparsity, which increases the likelihood of language models learning spurious patterns. To address this issue, prior research has focused on diversifying question…
Knowledge transfer from a complex high performing model to a simpler and potentially low performing one in order to enhance its performance has been of great interest over the last few years as it finds applications in important problems…
Multi-hop QA requires reasoning over multiple supporting facts to answer the question. However, the existing QA models always rely on shortcuts, e.g., providing the true answer by only one fact, rather than multi-hop reasoning, which is…
Retrieval-Augmented Generation (RAG) systems often struggle with imperfect retrieval, as traditional retrievers focus on lexical or semantic similarity rather than logical relevance. To address this, we propose \textbf{HopRAG}, a novel RAG…
Reasoning models enhance performance by tackling problems in a step-by-step manner, decomposing them into sub-problems and exploring long chains of thought before producing an answer. However, applying extended reasoning to every step…