@inproceedings{wang-etal-2026-fred,
title = "{FRED}-{S}em{B}ench: Evaluating Semantic Reliability in {LLM} Access to Macroeconomic Data",
author = "Wang, Wilson and
Han, Chandler and
Zhang, Peter",
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-1.19/",
pages = "237--242",
ISBN = "979-8-89176-466-8",
abstract = "Access to authoritative financial data does not ensure semantically correct answers: a language model may retrieve a valid observation associated with the wrong series, transformation, unit, or temporal interpretation. We introduce FRED-SemBench, a 200-question benchmark candidate over independently selected Federal Reserve Economic Data (FRED) concepts that separates retrieval failures from semantic data-access failures. We also instantiate Iris, an ontology-backed semantic layer whose versioned concept contracts bind user intent to provider series, transformations, units, temporal semantics, provenance, and declared coverage. A controlled comparison of an unaided model, FRED and Web access, and Iris reveals a reliability trade-off: raw retrieval substantially improves numerical answering while suppressing abstention and reducing clarification accuracy on underspecified queries. Within its pre-declared support set, Iris preserves the numerical benefit, restores clarification behavior, and attains the strongest strict accuracy, suggesting that this trade-off is not intrinsic to data access. These pilot findings motivate evaluating macroeconomic data access jointly in terms of semantic correctness, boundary behavior, coverage, and operational cost."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2026-fred">
<titleInfo>
<title>FRED-SemBench: Evaluating Semantic Reliability in LLM Access to Macroeconomic Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wilson</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chandler</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Zhang</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>Access to authoritative financial data does not ensure semantically correct answers: a language model may retrieve a valid observation associated with the wrong series, transformation, unit, or temporal interpretation. We introduce FRED-SemBench, a 200-question benchmark candidate over independently selected Federal Reserve Economic Data (FRED) concepts that separates retrieval failures from semantic data-access failures. We also instantiate Iris, an ontology-backed semantic layer whose versioned concept contracts bind user intent to provider series, transformations, units, temporal semantics, provenance, and declared coverage. A controlled comparison of an unaided model, FRED and Web access, and Iris reveals a reliability trade-off: raw retrieval substantially improves numerical answering while suppressing abstention and reducing clarification accuracy on underspecified queries. Within its pre-declared support set, Iris preserves the numerical benefit, restores clarification behavior, and attains the strongest strict accuracy, suggesting that this trade-off is not intrinsic to data access. These pilot findings motivate evaluating macroeconomic data access jointly in terms of semantic correctness, boundary behavior, coverage, and operational cost.</abstract>
<identifier type="citekey">wang-etal-2026-fred</identifier>
<location>
<url>https://aclanthology.org/2026.finnlp-1.19/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>237</start>
<end>242</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FRED-SemBench: Evaluating Semantic Reliability in LLM Access to Macroeconomic Data
%A Wang, Wilson
%A Han, Chandler
%A Zhang, Peter
%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 wang-etal-2026-fred
%X Access to authoritative financial data does not ensure semantically correct answers: a language model may retrieve a valid observation associated with the wrong series, transformation, unit, or temporal interpretation. We introduce FRED-SemBench, a 200-question benchmark candidate over independently selected Federal Reserve Economic Data (FRED) concepts that separates retrieval failures from semantic data-access failures. We also instantiate Iris, an ontology-backed semantic layer whose versioned concept contracts bind user intent to provider series, transformations, units, temporal semantics, provenance, and declared coverage. A controlled comparison of an unaided model, FRED and Web access, and Iris reveals a reliability trade-off: raw retrieval substantially improves numerical answering while suppressing abstention and reducing clarification accuracy on underspecified queries. Within its pre-declared support set, Iris preserves the numerical benefit, restores clarification behavior, and attains the strongest strict accuracy, suggesting that this trade-off is not intrinsic to data access. These pilot findings motivate evaluating macroeconomic data access jointly in terms of semantic correctness, boundary behavior, coverage, and operational cost.
%U https://aclanthology.org/2026.finnlp-1.19/
%P 237-242
Markdown (Informal)
[FRED-SemBench: Evaluating Semantic Reliability in LLM Access to Macroeconomic Data](https://aclanthology.org/2026.finnlp-1.19/) (Wang et al., FinNLP 2026)
ACL