@inproceedings{liu-etal-2026-cast,
title = "{CAST}: An Interpretable Evidence-Based Confidence Estimation Tool for {RAG} with Human-in-the-Loop Verification",
author = "Liu, Xutong and
Beumer, Morris Groot and
Osterrieder, Joerg Robert and
Baak, Max",
editor = "Huang, Jimin and
Lee, Yongjae and
Ananiadou, Sophia and
Chen, Hsin-Hsi and
Takamura, Hiroya and
Chen, Chung-Chi",
booktitle = "Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.finnlp-1.26/",
pages = "332--341",
ISBN = "979-8-89176-466-8",
abstract = "Large language models (LLMs) increasingly assist financial analysis tasks over filings, reports, and news via retrieval-augmented generation (RAG), but a human reviewer typically remains accountable for the final decision. In this setting, a confidence score must be more than well-calibrated: it must be evidence-based and explainable, so reviewers can see why an answer should be trusted. We introduce CAST (Confidence via Answer Support Testing), a Bayesian-inspired confidence method that compares a generated answer with a plausible competing alternative and evaluates how retrieved passages support each hypothesis. CAST produces both an answer-level confidence score and citation-level evidence for review. We also demonstrate CAST through an interactive reviewer-facing tool that visualizes supporting and opposing evidence for human verification. On 1,286 financial-report questions from MMDocRAG, CAST achieves the highest AUROC among seven evaluated methods (0.634 vs. 0.598 for the strongest baseline)."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2026-cast">
<titleInfo>
<title>CAST: An Interpretable Evidence-Based Confidence Estimation Tool for RAG with Human-in-the-Loop Verification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xutong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Morris</namePart>
<namePart type="given">Groot</namePart>
<namePart type="family">Beumer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joerg</namePart>
<namePart type="given">Robert</namePart>
<namePart type="family">Osterrieder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Max</namePart>
<namePart type="family">Baak</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 11th Workshop on Financial Technology and Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jimin</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongjae</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroya</namePart>
<namePart type="family">Takamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chung-Chi</namePart>
<namePart type="family">Chen</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">979-8-89176-466-8</identifier>
</relatedItem>
<abstract>Large language models (LLMs) increasingly assist financial analysis tasks over filings, reports, and news via retrieval-augmented generation (RAG), but a human reviewer typically remains accountable for the final decision. In this setting, a confidence score must be more than well-calibrated: it must be evidence-based and explainable, so reviewers can see why an answer should be trusted. We introduce CAST (Confidence via Answer Support Testing), a Bayesian-inspired confidence method that compares a generated answer with a plausible competing alternative and evaluates how retrieved passages support each hypothesis. CAST produces both an answer-level confidence score and citation-level evidence for review. We also demonstrate CAST through an interactive reviewer-facing tool that visualizes supporting and opposing evidence for human verification. On 1,286 financial-report questions from MMDocRAG, CAST achieves the highest AUROC among seven evaluated methods (0.634 vs. 0.598 for the strongest baseline).</abstract>
<identifier type="citekey">liu-etal-2026-cast</identifier>
<location>
<url>https://aclanthology.org/2026.finnlp-1.26/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>332</start>
<end>341</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CAST: An Interpretable Evidence-Based Confidence Estimation Tool for RAG with Human-in-the-Loop Verification
%A Liu, Xutong
%A Beumer, Morris Groot
%A Osterrieder, Joerg Robert
%A Baak, Max
%Y Huang, Jimin
%Y Lee, Yongjae
%Y Ananiadou, Sophia
%Y Chen, Hsin-Hsi
%Y Takamura, Hiroya
%Y Chen, Chung-Chi
%S Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-466-8
%F liu-etal-2026-cast
%X Large language models (LLMs) increasingly assist financial analysis tasks over filings, reports, and news via retrieval-augmented generation (RAG), but a human reviewer typically remains accountable for the final decision. In this setting, a confidence score must be more than well-calibrated: it must be evidence-based and explainable, so reviewers can see why an answer should be trusted. We introduce CAST (Confidence via Answer Support Testing), a Bayesian-inspired confidence method that compares a generated answer with a plausible competing alternative and evaluates how retrieved passages support each hypothesis. CAST produces both an answer-level confidence score and citation-level evidence for review. We also demonstrate CAST through an interactive reviewer-facing tool that visualizes supporting and opposing evidence for human verification. On 1,286 financial-report questions from MMDocRAG, CAST achieves the highest AUROC among seven evaluated methods (0.634 vs. 0.598 for the strongest baseline).
%U https://aclanthology.org/2026.finnlp-1.26/
%P 332-341
Markdown (Informal)
[CAST: An Interpretable Evidence-Based Confidence Estimation Tool for RAG with Human-in-the-Loop Verification](https://aclanthology.org/2026.finnlp-1.26/) (Liu et al., FinNLP 2026)
ACL