Research

Paper

TESTING March 17, 2026

CounterRefine: Answer-Conditioned Counterevidence Retrieval for Inference-Time Knowledge Repair in Factual Question Answering

Authors

Tianyi Huang, Ying Kai Deng

Abstract

In factual question answering, many errors are not failures of access but failures of commitment: the system retrieves relevant evidence, yet still settles on the wrong answer. We present CounterRefine, a lightweight inference-time repair layer for retrieval-grounded question answering. CounterRefine first produces a short answer from retrieved evidence, then gathers additional support and conflicting evidence with follow-up queries conditioned on that draft answer, and finally applies a restricted refinement step that outputs either KEEP or REVISE, with proposed revisions accepted only if they pass deterministic validation. In effect, CounterRefine turns retrieval into a mechanism for testing a provisional answer rather than merely collecting more context. On the full SimpleQA benchmark, CounterRefine improves a matched GPT-5 Baseline-RAG by 5.8 points and reaches a 73.1 percent correct rate, while exceeding the reported one-shot GPT-5.4 score by roughly 40 points. These findings suggest a simple but important direction for knowledgeable foundation models: beyond accessing evidence, they should also be able to use that evidence to reconsider and, when necessary, repair their own answers.

Metadata

arXiv ID: 2603.16091
Provider: ARXIV
Primary Category: cs.CL
Published: 2026-03-17
Fetched: 2026-03-18 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.16091v1</id>\n    <title>CounterRefine: Answer-Conditioned Counterevidence Retrieval for Inference-Time Knowledge Repair in Factual Question Answering</title>\n    <updated>2026-03-17T03:27:25Z</updated>\n    <link href='https://arxiv.org/abs/2603.16091v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.16091v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>In factual question answering, many errors are not failures of access but failures of commitment: the system retrieves relevant evidence, yet still settles on the wrong answer. We present CounterRefine, a lightweight inference-time repair layer for retrieval-grounded question answering. CounterRefine first produces a short answer from retrieved evidence, then gathers additional support and conflicting evidence with follow-up queries conditioned on that draft answer, and finally applies a restricted refinement step that outputs either KEEP or REVISE, with proposed revisions accepted only if they pass deterministic validation. In effect, CounterRefine turns retrieval into a mechanism for testing a provisional answer rather than merely collecting more context. On the full SimpleQA benchmark, CounterRefine improves a matched GPT-5 Baseline-RAG by 5.8 points and reaches a 73.1 percent correct rate, while exceeding the reported one-shot GPT-5.4 score by roughly 40 points. These findings suggest a simple but important direction for knowledgeable foundation models: beyond accessing evidence, they should also be able to use that evidence to reconsider and, when necessary, repair their own answers.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CL'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-03-17T03:27:25Z</published>\n    <arxiv:primary_category term='cs.CL'/>\n    <author>\n      <name>Tianyi Huang</name>\n    </author>\n    <author>\n      <name>Ying Kai Deng</name>\n    </author>\n  </entry>"
}