Pith. sign in

REVIEW 1 cited by

Merging Generated and Retrieved Knowledge for Open-Domain QA

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2310.14393 v1 pith:AROT3ZGU submitted 2023-10-22 cs.CL cs.AI

classification cs.CLcs.AI
keywords knowledgeopen-domainpassagesretrievedcomboconflictsframeworkllms
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows

    cs.AI 2025-06 conditional novelty 6.0 of 10

    LLM agents frequently switch correct answers after one round of misleading feedback, and the new WAFER-QA benchmark measures this with web-backed critiques.

Pith tools