CORTEXA
← Browse
arxivcs.CLcs.AI2026-06-30

When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors

Yuqing Yang, Qi Zhu, Zhen Han, Boran Han, Zhengyuan Shen, Shuai Wang, Vassilis N. Ioannidis, Huzefa Rangwala

While large language models (LLMs) perform well on table tasks, they still make data referencing errors (DREs), i.e., incorrectly citing or omitting table values, despite understanding the table structure. Beyond final-answer accuracy, DREs directly compromise the correctness and reliability of intermediate reasoning steps. Yet prior studies have only offered limited, small-scale analyses. In this work, we present the first systematic evaluation of tabular data referencing errors across different models and tasks. Our results show that DREs occur across all tested models (1.7B to 20B parameters). Furthermore, we demonstrate that incorporating data referencing as a critic significantly improves answer accuracy up to 12.0%, through critic-based filtering and rejection sampling. Finally, we trained a lightweight 4B-parameter critic model that achieves an average F1 score of 78.2% in detecting both in-distribution and out-of-distribution DREs, and effectively assists inference for larger models.

View free PDFSource page

Related papers

arxivcs.LGcs.AIcs.CL2026-07-15

Data-Efficient Adaptation of LLMs via Attention Head Reweighting

Tuomas Oikarinen, Zixiao Chen, Charlotte Siska, Tsui-Wei Weng, Chandan Singh, Jianfeng Gao

Learning effectively from limited data is critical in domains like security where labeled examples are scarce. Large language models (LLMs) have demonstrated some capabilities for data-efficient learning, especially through parameter-efficient adaptation methods, but continue to…

View free PDFSource page
arxivcs.SEcs.AIcs.CL2026-07-14

Code-MUE: Measuring Code LLMs' Uncertainty through Execution-based Semantic Interaction Graphs

Xiaoning Ren, Yinxing Xue, Lei Ma, Yuheng Huang

As Code Large Language Models (LLMs) become central to modern software engineering, their inherent stochasticity poses significant real-world risks, where even minor errors can lead to severe functional, security, or safety consequences. Reliable automation, therefore, demands th…

View free PDFSource page
arxivcs.CLcs.AIcs.CY2026-06-26

Correct codes for the wrong reasons? validating LLMs as measurement instruments for theoretical constructs

Manuel Pita

When a large language model (LLM) codes a construct in text as a human annotator would, that agreement makes the LLM a reliable coder. Yet reliability leaves construct validity untouched. The instrument may be theory-naive, reaching the code through a correlate that meets none of…

View free PDFSource page
arxivcs.CLcs.AI2026-07-07

Data Analysis in the Wild: Benchmarking Large Language Models Against Real-World Data Complexities

So Hasegawa, Shailaja Keyur Sampat, Lei Liu, Wei-Peng Chen

Current benchmarks for evaluating Large Language Models (LLMs) in data analysis often fail to reflect real-world settings. They typically focus on fact retrieval from small tables and overlook the challenges of large multi-tabular datasets, external knowledge integration, and exp…

View free PDFSource page
arxivcs.CLcs.AI2026-07-05

Risk-Constrained Freshness-Aware Semantic Caching for Open-Web Retrieval-Augmented LLMs

Muhammad Mansoor, Tahir Ahmad, Yeo-Chan Yoon

Semantic caching reduces the latency and cost of retrieval-augmented generation (RAG) by serving cached answers to semantically similar queries, but most existing methods do not model the time-varying freshness of open-web evidence. We present FreshCache, a three-tier semantic ca…

View free PDFSource page
arxivcs.CLcs.AI2026-07-03

The Role of Prompt Language and Translation-Theory-Driven Prompts in Large Language Models: A Case Study on Spanish-Chinese Journalistic Translation

Haohong Lai, Weijia Li

This study examines how prompt language and translation theory-driven prompt design influence the quality of Spanish-Chinese journalistic translations generated by GPT-5.2. A parallel corpus of four editorials from El Pais was translated under 48 experimental conditions (4 prompt…

View free PDFSource page