paper-with-me

홈 › Papers

Merging Generated and Retrieved Knowledge for Open-Domain QA

2023-10-22 · Yunxiang Zhang, Muhammad Khalifa, Lajanugen Logeswaran, Moontae Lee, Honglak Lee, Lu Wang

Open-domain question answering (QA) systems are often built with retrieval modules. However, retrieving passages from a given source is known to suffer from insufficient knowledge coverage. Alternatively, prompting large language models (LLMs) to generate contextual passages based on their parametric knowledge has been shown to improve QA performance. Yet, LLMs tend to "hallucinate" content that conflicts with the retrieved knowledge. Based on the intuition that answers supported by both sources are more likely to be correct, we propose COMBO, a Compatibility-Oriented knowledge Merging for Better Open-domain QA framework, to effectively leverage the two sources of information. Concretely, we match LLM-generated passages with retrieved counterparts into compatible pairs, based on discriminators trained with silver compatibility labels. Then a Fusion-in-Decoder-based reader model handles passage pairs to arrive at the final answer. Experiments show that COMBO outperforms competitive baselines on three out of four tested open-domain QA benchmarks. Further analysis reveals that our proposed framework demonstrates greater efficacy in scenarios with a higher degree of knowledge conflicts.

📄 PDF Abstract BibTeX arXiv:2310.14393

Code (1)

yunx-z/combo 공식 구현 pytorch

Tasks

DecoderOpen-Domain Question AnsweringQuestion AnsweringRetrieval

Similar Papers 제목 키워드 기반

Improving Generated and Retrieved Knowledge Combination Through Zero-shot Generation

2024-12-25 · Xinkai Du, Quanjie Han, Chao Lv, Yan Liu 외

Open-domain Question Answering (QA) has garnered substantial interest by combining the advantages of faithfully retrieved passages and relevant passages generated through Large Language Models (LLMs). However, there is a…

Open-Domain Question AnsweringQuestion AnsweringRerankingRe-Ranking+1

QPaug: Question and Passage Augmentation for Open-Domain Question Answering of LLMs

2024-06-20 · Minsang Kim, Cheoneum Park, Seungjun Baek

Retrieval-augmented generation (RAG) has received much attention for Open-domain question-answering (ODQA) tasks as a means to compensate for the parametric knowledge of large language models (LLMs). While previous appro…

Open-Domain Question AnsweringQuestion AnsweringRAGRetrieval+1

CoCoA: Collaborative Chain-of-Agents for Parametric-Retrieved Knowledge Synergy

2025-08-03 · Yi Jiang, Sendong Zhao, Jianbo Li, Haochun Wang 외 arxiv

Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs), especially for knowledge-intensive tasks. Despite its advantages, current RAG methods often struggle to fully exploit knowledge during generatio…

Knowledge Fusion and Semantic Knowledge Ranking for Open Domain Question Answering

2020-04-07 · Pratyay Banerjee, Chitta Baral

Open Domain Question Answering requires systems to retrieve external knowledge and perform multi-hop reasoning by composing knowledge spread over multiple sentences. In the recently introduced open domain question answer…

Information RetrievalOpen-Domain Question AnsweringQuestion AnsweringRetrieval

Answering Science Exam Questions Using Query Rewriting with Background Knowledge

2018-09-15 · Ryan Musa, Xiaoyan Wang, Achille Fokoue, Nicholas Mattei 외

Open-domain question answering (QA) is an important problem in AI and NLP that is emerging as a bellwether for progress on the generalizability of AI methods and techniques. Much of the progress in open-domain QA systems…

ARCInformation RetrievalMultiple-choiceNatural Language Inference+3