Robustifying Multi-hop QA through Pseudo-Evidentiality Training
This paper studies the bias problem of multi-hop question answering models, of answering correctly without correct reasoning. One way to robustify these models is by supervising to not only answer right, but also with right reasoning chains. An existing direction is to annotate reasoning chains to train models, requiring expensive additional annotations. In contrast, we propose a new approach to learn evidentiality, deciding whether the answer prediction is supported by correct evidences, without such annotations. Instead, we compare counterfactual changes in answer confidence with and without evidence sentences, to generate "pseudo-evidentiality" annotations. We validate our proposed model on an original set and challenge set in HotpotQA, showing that our method is accurate and robust in multi-hop reasoning.
Code (0)
등록된 구현이 없습니다.
Tasks
counterfactualMulti-hop Question AnsweringQuestion AnsweringSimilar Papers 제목 키워드 기반
Evidentiality-guided Generation for Knowledge-Intensive NLP Tasks
Retrieval-augmented generation models have shown state-of-the-art performance across many knowledge-intensive NLP tasks such as open question answering and fact verification. These models are trained to generate a final …
Fact VerificationMemorizationMulti-Task LearningOpen-Domain Question Answering+4Evidentiality-guided Generation for Knowledge-Intensive NLP Tasks
Retrieval-augmented generation models have shown state-of-the-art performance across many knowledge-intensive NLP tasks such as open question answering and fact verification. These models are trained to generate the fina…
AttributeFact VerificationMemorizationMulti-Task Learning+4ECoRAG: Evidentiality-guided Compression for Long Context RAG
Large Language Models (LLMs) have shown remarkable performance in Open-Domain Question Answering (ODQA) by leveraging external documents through Retrieval-Augmented Generation (RAG). To reduce RAG overhead, from longer c…
Answer GenerationOpen-Domain Question AnsweringQuestion AnsweringRAG+1Evidentiality-aware Retrieval for Overcoming Abstractiveness in Open-Domain Question Answering
The long-standing goal of dense retrievers in abtractive open-domain question answering (ODQA) tasks is to learn to capture evidence passages among relevant passages for any given query, such that the reader produce fact…
Contrastive LearningcounterfactualOpen-Domain Question AnsweringPassage Retrieval+3