@inproceedings{albarede-etal-2026-earal,
title = "{EARAL}: Efficient Attribution of Retrieval-Augmented Answer Generation using Logits",
author = "Albarede, Lucas and
Moreno, Jose G and
Tamine, Lynda and
Lefeuvre, Luce",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.530/",
pages = "12233--12247",
ISBN = "979-8-89176-459-0",
abstract = "Large Language Models (LLMs) generate grounded answers using Retrieval-Augmented Generation (RAG), reducing hallucinations. Prior work has focused on answer and attribution correctness, with recent studies exploring faithfulness through internal signals that reflect the model{'}s decision process. However, these approaches often introduce latency and do not tightly align token generation with attribution. We propose EARAL, a novel attribution method for RAG that improves faithfulness through joint answer generation and generation-time attribution with minimal overhead. Documents are marked with special token identifiers, whose logits estimate their contribution during generation and are aggregated into document-level attributions. On the Trust-Align benchmark for trustworthy attributed generation, EARAL outperforms state-of-the-art methods across metrics. Additional analysis shows low latency, robustness, and strong alignment with faithfulness."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="albarede-etal-2026-earal">
<titleInfo>
<title>EARAL: Efficient Attribution of Retrieval-Augmented Answer Generation using Logits</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lucas</namePart>
<namePart type="family">Albarede</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jose</namePart>
<namePart type="given">G</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lynda</namePart>
<namePart type="family">Tamine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luce</namePart>
<namePart type="family">Lefeuvre</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>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</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">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Large Language Models (LLMs) generate grounded answers using Retrieval-Augmented Generation (RAG), reducing hallucinations. Prior work has focused on answer and attribution correctness, with recent studies exploring faithfulness through internal signals that reflect the model’s decision process. However, these approaches often introduce latency and do not tightly align token generation with attribution. We propose EARAL, a novel attribution method for RAG that improves faithfulness through joint answer generation and generation-time attribution with minimal overhead. Documents are marked with special token identifiers, whose logits estimate their contribution during generation and are aggregated into document-level attributions. On the Trust-Align benchmark for trustworthy attributed generation, EARAL outperforms state-of-the-art methods across metrics. Additional analysis shows low latency, robustness, and strong alignment with faithfulness.</abstract>
<identifier type="citekey">albarede-etal-2026-earal</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.530/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>12233</start>
<end>12247</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T EARAL: Efficient Attribution of Retrieval-Augmented Answer Generation using Logits
%A Albarede, Lucas
%A Moreno, Jose G.
%A Tamine, Lynda
%A Lefeuvre, Luce
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F albarede-etal-2026-earal
%X Large Language Models (LLMs) generate grounded answers using Retrieval-Augmented Generation (RAG), reducing hallucinations. Prior work has focused on answer and attribution correctness, with recent studies exploring faithfulness through internal signals that reflect the model’s decision process. However, these approaches often introduce latency and do not tightly align token generation with attribution. We propose EARAL, a novel attribution method for RAG that improves faithfulness through joint answer generation and generation-time attribution with minimal overhead. Documents are marked with special token identifiers, whose logits estimate their contribution during generation and are aggregated into document-level attributions. On the Trust-Align benchmark for trustworthy attributed generation, EARAL outperforms state-of-the-art methods across metrics. Additional analysis shows low latency, robustness, and strong alignment with faithfulness.
%U https://aclanthology.org/2026.emnlp-main.530/
%P 12233-12247
Markdown (Informal)
[EARAL: Efficient Attribution of Retrieval-Augmented Answer Generation using Logits](https://aclanthology.org/2026.emnlp-main.530/) (Albarede et al., EMNLP 2026)
ACL