@inproceedings{ghafouri-2026-nutrichat,
title = "{N}utri{C}hat: Evaluating Safety-Aware Retrieval-Augmented Generation for Nutrition Textbook Question Answering",
author = "Ghafouri, Hadis",
editor = "T.Y.S.S., Santosh and
Agarwal, Amit and
Gupta, Vivek and
Kementchedjhieva, Yova and
Garimella, Aparna and
Hou, Yufang",
booktitle = "The Proceedings of Workshop on Document Intelligence and Understanding",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.docinsights-1.12/",
pages = "163--173",
ISBN = "979-8-89176-477-4",
abstract = "Large language models can answer nutrition questions fluently, but educational assistants must also rely on the assigned source, recognize unsupported requests, and respond safely to medically sensitive or adversarial questions. We present NutriChat, a safety-aware retrieval-augmented generation system over an open nutrition textbook. Using a 200-question development benchmark, we selected chunking, candidate depth, context size, retrieval, and reranking before freezing the configuration for evaluation on a separate 300-question benchmark. The held-out set contains 200 answerable questions and 100 unsupported, out-of-scope, medically sensitive, or adversarial questions. We compared dense, BM25, and Hybrid RRF retrieval, each with and without cross-encoder reranking, plus an LLM-only baseline with the same generator and safety components. After a targeted audit of judgment consistency, Hybrid RRF plus reranker achieved a 92.0{\%} pass rate, compared with 84.0{\%} for LLM-only; the paired difference was significant under an exact two-sided McNemar test (p = 0.00150). It also reached 94.5{\%} Page hit@3 and 0.880 MRR. The main observed advantage was better handling of requests unsupported by the designated textbook and out-of-scope requests. Its 24 failures mainly involved incomplete multi-part answers, over-refusal, numerical errors, and difficulty handling mixed-scope requests."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ghafouri-2026-nutrichat">
<titleInfo>
<title>NutriChat: Evaluating Safety-Aware Retrieval-Augmented Generation for Nutrition Textbook Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hadis</namePart>
<namePart type="family">Ghafouri</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>The Proceedings of Workshop on Document Intelligence and Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Santosh</namePart>
<namePart type="family">T.Y.S.S.</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amit</namePart>
<namePart type="family">Agarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yova</namePart>
<namePart type="family">Kementchedjhieva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aparna</namePart>
<namePart type="family">Garimella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yufang</namePart>
<namePart type="family">Hou</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">979-8-89176-477-4</identifier>
</relatedItem>
<abstract>Large language models can answer nutrition questions fluently, but educational assistants must also rely on the assigned source, recognize unsupported requests, and respond safely to medically sensitive or adversarial questions. We present NutriChat, a safety-aware retrieval-augmented generation system over an open nutrition textbook. Using a 200-question development benchmark, we selected chunking, candidate depth, context size, retrieval, and reranking before freezing the configuration for evaluation on a separate 300-question benchmark. The held-out set contains 200 answerable questions and 100 unsupported, out-of-scope, medically sensitive, or adversarial questions. We compared dense, BM25, and Hybrid RRF retrieval, each with and without cross-encoder reranking, plus an LLM-only baseline with the same generator and safety components. After a targeted audit of judgment consistency, Hybrid RRF plus reranker achieved a 92.0% pass rate, compared with 84.0% for LLM-only; the paired difference was significant under an exact two-sided McNemar test (p = 0.00150). It also reached 94.5% Page hit@3 and 0.880 MRR. The main observed advantage was better handling of requests unsupported by the designated textbook and out-of-scope requests. Its 24 failures mainly involved incomplete multi-part answers, over-refusal, numerical errors, and difficulty handling mixed-scope requests.</abstract>
<identifier type="citekey">ghafouri-2026-nutrichat</identifier>
<location>
<url>https://aclanthology.org/2026.docinsights-1.12/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>163</start>
<end>173</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NutriChat: Evaluating Safety-Aware Retrieval-Augmented Generation for Nutrition Textbook Question Answering
%A Ghafouri, Hadis
%Y T.Y.S.S., Santosh
%Y Agarwal, Amit
%Y Gupta, Vivek
%Y Kementchedjhieva, Yova
%Y Garimella, Aparna
%Y Hou, Yufang
%S The Proceedings of Workshop on Document Intelligence and Understanding
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-477-4
%F ghafouri-2026-nutrichat
%X Large language models can answer nutrition questions fluently, but educational assistants must also rely on the assigned source, recognize unsupported requests, and respond safely to medically sensitive or adversarial questions. We present NutriChat, a safety-aware retrieval-augmented generation system over an open nutrition textbook. Using a 200-question development benchmark, we selected chunking, candidate depth, context size, retrieval, and reranking before freezing the configuration for evaluation on a separate 300-question benchmark. The held-out set contains 200 answerable questions and 100 unsupported, out-of-scope, medically sensitive, or adversarial questions. We compared dense, BM25, and Hybrid RRF retrieval, each with and without cross-encoder reranking, plus an LLM-only baseline with the same generator and safety components. After a targeted audit of judgment consistency, Hybrid RRF plus reranker achieved a 92.0% pass rate, compared with 84.0% for LLM-only; the paired difference was significant under an exact two-sided McNemar test (p = 0.00150). It also reached 94.5% Page hit@3 and 0.880 MRR. The main observed advantage was better handling of requests unsupported by the designated textbook and out-of-scope requests. Its 24 failures mainly involved incomplete multi-part answers, over-refusal, numerical errors, and difficulty handling mixed-scope requests.
%U https://aclanthology.org/2026.docinsights-1.12/
%P 163-173
Markdown (Informal)
[NutriChat: Evaluating Safety-Aware Retrieval-Augmented Generation for Nutrition Textbook Question Answering](https://aclanthology.org/2026.docinsights-1.12/) (Ghafouri, DocInsights 2026)
ACL