@inproceedings{shihab-etal-2026-grounded,
title = "Grounded Decoding: Retrieval-Anchored Probability Fusion for Faithful {RAG}",
author = "Shihab, Ibne Farabi and
Afrin, Fariya and
Akter, Sanjeda and
Sharma, Anuj",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.544/",
pages = "11451--11472",
ISBN = "979-8-89176-462-0",
abstract = "As retrieval-augmented generation (RAG) systems scale, ensuring faithful grounding in external evidence remains challenging. Large language models may still rely on parametric knowledge when it conflicts with retrieved information. We propose Grounded Decoding, a training-free decoding framework that improves factual consistency in RAG without modifying model parameters. At each generation step, our method constructs two matched-prompt distributions: a full RAG distribution conditioned on the query, retrieved documents, and generated prefix, and a retrieval-only distribution conditioned solely on the retrieved evidence and the same prefix. We derive the final next-token distribution as the unique solution to a KL-barycenter objective over the probability simplex, resulting in a normalized geometric fusion of the two distributions. The formulation recovers standard RAG when the grounding weight is zero and progressively shifts probability mass toward retrieved evidence as grounding strength increases. We further introduce a conflict-aware adaptive weighting scheme that adjusts grounding strength based on distributional disagreement and retriever confidence. Experiments on ALCE, Natural Questions, and FActScore show consistent improvements in factual accuracy and citation quality over standard RAG and competitive decoding-time baselines while maintaining fluency. These results suggest that probability-level fusion offers an effective and efficient alternative to logit-level intervention for faithful RAG decoding."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shihab-etal-2026-grounded">
<titleInfo>
<title>Grounded Decoding: Retrieval-Anchored Probability Fusion for Faithful RAG</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ibne</namePart>
<namePart type="given">Farabi</namePart>
<namePart type="family">Shihab</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fariya</namePart>
<namePart type="family">Afrin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sanjeda</namePart>
<namePart type="family">Akter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anuj</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>As retrieval-augmented generation (RAG) systems scale, ensuring faithful grounding in external evidence remains challenging. Large language models may still rely on parametric knowledge when it conflicts with retrieved information. We propose Grounded Decoding, a training-free decoding framework that improves factual consistency in RAG without modifying model parameters. At each generation step, our method constructs two matched-prompt distributions: a full RAG distribution conditioned on the query, retrieved documents, and generated prefix, and a retrieval-only distribution conditioned solely on the retrieved evidence and the same prefix. We derive the final next-token distribution as the unique solution to a KL-barycenter objective over the probability simplex, resulting in a normalized geometric fusion of the two distributions. The formulation recovers standard RAG when the grounding weight is zero and progressively shifts probability mass toward retrieved evidence as grounding strength increases. We further introduce a conflict-aware adaptive weighting scheme that adjusts grounding strength based on distributional disagreement and retriever confidence. Experiments on ALCE, Natural Questions, and FActScore show consistent improvements in factual accuracy and citation quality over standard RAG and competitive decoding-time baselines while maintaining fluency. These results suggest that probability-level fusion offers an effective and efficient alternative to logit-level intervention for faithful RAG decoding.</abstract>
<identifier type="citekey">shihab-etal-2026-grounded</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.544/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>11451</start>
<end>11472</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Grounded Decoding: Retrieval-Anchored Probability Fusion for Faithful RAG
%A Shihab, Ibne Farabi
%A Afrin, Fariya
%A Akter, Sanjeda
%A Sharma, Anuj
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F shihab-etal-2026-grounded
%X As retrieval-augmented generation (RAG) systems scale, ensuring faithful grounding in external evidence remains challenging. Large language models may still rely on parametric knowledge when it conflicts with retrieved information. We propose Grounded Decoding, a training-free decoding framework that improves factual consistency in RAG without modifying model parameters. At each generation step, our method constructs two matched-prompt distributions: a full RAG distribution conditioned on the query, retrieved documents, and generated prefix, and a retrieval-only distribution conditioned solely on the retrieved evidence and the same prefix. We derive the final next-token distribution as the unique solution to a KL-barycenter objective over the probability simplex, resulting in a normalized geometric fusion of the two distributions. The formulation recovers standard RAG when the grounding weight is zero and progressively shifts probability mass toward retrieved evidence as grounding strength increases. We further introduce a conflict-aware adaptive weighting scheme that adjusts grounding strength based on distributional disagreement and retriever confidence. Experiments on ALCE, Natural Questions, and FActScore show consistent improvements in factual accuracy and citation quality over standard RAG and competitive decoding-time baselines while maintaining fluency. These results suggest that probability-level fusion offers an effective and efficient alternative to logit-level intervention for faithful RAG decoding.
%U https://aclanthology.org/2026.findings-emnlp.544/
%P 11451-11472
Markdown (Informal)
[Grounded Decoding: Retrieval-Anchored Probability Fusion for Faithful RAG](https://aclanthology.org/2026.findings-emnlp.544/) (Shihab et al., Findings 2026)
ACL