Consistency-Driven Iterative Retrieval-Augmented Generation Using Cross-Evidence Agreement as a Stopping Signal

Iterative retrieval-augmented generation improves multi-hop question answering, but deciding when to stop retrieving remains an open problem. Fixed retrieval depths spend the same effort on every question, and confidence-based triggers inherit the overconfidence of the generator. This paper studies a stopping test that needs no training and no access to token probabilities. After each retrieval round the generator answers once from all retrieved passages and again from leave-one-group-out subsets of them. Retrieval stops only when every subset reproduces the full answer. Otherwise the facts that the generator reports as missing become the next queries. A pilot study on 100 HotpotQA questions shows that partial agreement between subsets carries no usable signal, which motivates the unanimity rule. The method is then evaluated on 300 held-out HotpotQA questions against single-pass retrieval, fixed-depth retrieval, and a self-consistency twin that makes the same generator calls per round but resamples answers from unchanged evidence. The method matches fixed-depth retrieval on answer F1, 61.3 against 61.2 percent, while making 9.1 generator calls per question against 3.0, and no difference in F1 between the method and either iterative baseline has a confidence interval that excludes zero. Unanimous agreement identifies reliable answers under both controllers, but resampling flags 167 of 252 answers at 69.5 percent precision where evidence removal flags 41 at 75.6 percent, so varying the evidence yields a stricter test rather than a better one.

Authors

Institutions

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-18
DOI
https://doi.org/10.5281/zenodo.24347579
Primary Topic
Topic Modeling
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Consistency-Driven Iterative Retrieval-Augmented Generation Using Cross-Evidence Agreement as a Stopping Signal

Krishan Kumar Sah, Adish Jain
1 links
Zenodo (CERN European Organization for Nuclear Research)
Topic Modeling
article

Consistency-Driven Iterative Retrieval-Augmented Generation Using Cross-Evidence Agreement as a Stopping Signal

Krishan Kumar Sah, Adish Jain
article en

Abstract

Iterative retrieval-augmented generation improves multi-hop question answering, but deciding when to stop retrieving remains an open problem. Fixed retrieval depths spend the same effort on every question, and confidence-based triggers inherit the overconfidence of the generator. This paper studies a stopping test that needs no training and no access to token probabilities. After each retrieval round the generator answers once from all retrieved passages and again from leave-one-group-out subsets of them. Retrieval stops only when every subset reproduces the full answer. Otherwise the facts that the generator reports as missing become the next queries. A pilot study on 100 HotpotQA questions shows that partial agreement between subsets carries no usable signal, which motivates the unanimity rule. The method is then evaluated on 300 held-out HotpotQA questions against single-pass retrieval, fixed-depth retrieval, and a self-consistency twin that makes the same generator calls per round but resamples answers from unchanged evidence. The method matches fixed-depth retrieval on answer F1, 61.3 against 61.2 percent, while making 9.1 generator calls per question against 3.0, and no difference in F1 between the method and either iterative baseline has a confidence interval that excludes zero. Unanimous agreement identifies reliable answers under both controllers, but resampling flags 167 of 252 answers at 69.5 percent precision where evidence removal flags 41 at 75.6 percent, so varying the evidence yields a stricter test rather than a better one.

Zenodo (CERN European Organization for Nuclear Research)
Chitkara University (IN)
Topic Modeling
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon