paper-with-me

Papers

Robustifying Multi-hop QA through Pseudo-Evidentiality Training

2021-07-07 · ACL 2021 5 · Kyungjae Lee, Seung-won Hwang, Sang-eun Han, Dohyeon Lee

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.

📄 PDF Abstract BibTeX arXiv:2107.03242

Code (0)

등록된 구현이 없습니다.

Tasks

counterfactualMulti-hop Question AnsweringQuestion Answering

Similar Papers 제목 키워드 기반

Evidentiality-guided Generation for Knowledge-Intensive NLP Tasks

2022-01-16 · ACL ARR January 2022 1 · Anonymous

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+4

Evidentiality-guided Generation for Knowledge-Intensive NLP Tasks

2021-12-16 · NAACL 2022 7 · Akari Asai, Matt Gardner, Hannaneh Hajishirzi

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+4

ECoRAG: Evidentiality-guided Compression for Long Context RAG

2025-06-05 · Yeonseok Jeong, Jinsu Kim, Dohyeon Lee, Seung-won Hwang

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+1

Evidentiality-aware Retrieval for Overcoming Abstractiveness in Open-Domain Question Answering

2023-04-06 · Yongho Song, Dahyun Lee, Myungha Jang, Seung-won Hwang 외

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

Evidentiality, Alethic Modality and Temporal Modifiers: The Case of Benlái vs. Yuánlái in Mandarin Chinese

2018-12-01 · PACLIC 2018 12 · Jiun-Shiung Wu