English
Related papers

Related papers: When prompt perturbations break your A/B test: A v…

200 papers

Large language models (LLMs) have achieved impressive performance across various mathematical reasoning benchmarks. However, there are increasing debates regarding whether these models truly understand and apply mathematical knowledge or…

Computation and Language · Computer Science 2024-07-03 Qintong Li , Leyang Cui , Xueliang Zhao , Lingpeng Kong , Wei Bi

Standard tests of the "no-treatment-effect" hypothesis for a comparative experiment include permutation tests, the Wilcoxon rank sum test, two-sample $t$ tests, and Fisher-type randomization tests. Practitioners are aware that these…

Methodology · Statistics 2015-09-11 Joseph B. Lang

Generative Large Language Models (LLMs) infer user's demographic information from subtle cues in the conversation -- a phenomenon called implicit personalization. Prior work has shown that such inferences can lead to lower quality responses…

Computation and Language · Computer Science 2025-09-17 Vera Neplenbroek , Arianna Bisazza , Raquel Fernández

Large language models (LLMs) are prone to hallucinations and sensitive to prompt perturbations, often resulting in inconsistent or unreliable generated text. Different methods have been proposed to mitigate such hallucinations and…

Computation and Language · Computer Science 2025-11-25 Xiaoyuan Wu , Weiran Lin , Omer Akgul , Lujo Bauer

LLMs are sensitive to prompting, with task performance often hinging on subtle, sometimes imperceptible variations in phrasing. As a result, crafting effective prompts manually remains challenging and time-consuming. Recent automatic…

Computation and Language · Computer Science 2025-12-01 Pawel Batorski , Paul Swoboda

This paper develops permutation versions of identification-robust tests in linear instrumental variables (IV) regression. Unlike the existing randomization and rank-based tests in which independence between the instruments and the error…

Econometrics · Economics 2024-07-24 Purevdorj Tuvaandorj

Graph-structured data underpins applications from citation analysis and social-network modeling to molecular design and knowledge-graph construction, and Large Language Models (LLMs) are increasingly used as prompt-driven graph…

Social and Information Networks · Computer Science 2026-05-20 Zihe Wei , Sheng Xiang , Ying Zhang , Changjun Jiang

The Political Compass Test (PCT) and similar surveys are commonly used to assess political bias in auto-regressive LLMs. Our rigorous statistical experiments show that while changes to standard generation parameters have minimal effect on…

Computers and Society · Computer Science 2025-11-13 Sadia Kamal , Lalu Prasad Yadav Prakash , S M Rafiuddin , Mohammed Rakib , Atriya Sen , Sagnik Ray Choudhury

Pretrained neural language models (LMs) are prone to generating racist, sexist, or otherwise toxic language which hinders their safe deployment. We investigate the extent to which pretrained LMs can be prompted to generate toxic language,…

Computation and Language · Computer Science 2020-09-29 Samuel Gehman , Suchin Gururangan , Maarten Sap , Yejin Choi , Noah A. Smith

A fundamental assumption underling any Hypothesis Testing (HT) problem is that the available data follow the parametric model assumed to derive the test statistic. Nevertheless, a perfect match between the true and the assumed data models…

Signal Processing · Electrical Eng. & Systems 2017-09-27 S. Fortunati , M. S. Greco , F. Gini

This paper studies gender bias in machine translation through the lens of Large Language Models (LLMs). Four widely-used test sets are employed to benchmark various base LLMs, comparing their translation quality and gender bias against…

Computation and Language · Computer Science 2024-07-29 Aleix Sant , Carlos Escolano , Audrey Mash , Francesca De Luca Fornaciari , Maite Melero

Despite their linguistic prowess, LLMs have been shown to be vulnerable to small input perturbations. While robustness to local adversarial changes has been studied, robustness to global modifications such as different linguistic styles…

Computation and Language · Computer Science 2025-07-08 Pulkit Arora , Akbar Karimi , Lucie Flek

Linguistic evaluations of how well LMs generalize to produce or understand language often implicitly take for granted that natural languages are generated by symbolic rules. According to this perspective, grammaticality is determined by…

Computation and Language · Computer Science 2025-09-19 Leonie Weissweiler , Kyle Mahowald , Adele Goldberg

Recent research has shown that hallucinations, omissions, and biases are prevalent in everyday use-cases of LLMs. However, chatbots used in medical contexts must provide consistent advice in situations where non-medical factors are…

Computation and Language · Computer Science 2025-11-05 Jonathan Liu , Haoling Qiu , Jonathan Lasko , Damianos Karakos , Mahsa Yarmohammadi , Mark Dredze

Counterfactual prompting (i.e., perturbing a single factor and measuring output change) is widely used to evaluate things like LLM bias and CoT faithfulness. But in this work we argue that observed effects cannot be attributed to the…

Computation and Language · Computer Science 2026-05-05 Zihao Yang , Mosh Levy , Yoav Goldberg , Byron C. Wallace

Evaluating pragmatic reasoning in large language models (LLMs) remains challenging because model behavior can vary depending on evaluation methods. Previous studies suggest that prompt-based judgments may diverge from models' internal…

Computation and Language · Computer Science 2026-05-12 Ye-eun Cho

Generative Agent-Based Models (GABMs) powered by large language models (LLMs) offer promising potential for empirical logistics and supply chain management (LSCM) research by enabling realistic simulation of complex human behaviors. Unlike…

Multiagent Systems · Computer Science 2025-08-29 Vincent E. Castillo

Large language models (LLMs) have demonstrated impressive capabilities across various tasks, but their performance is highly sensitive to the prompts utilized. This variability poses challenges for accurate assessment and user satisfaction.…

Computation and Language · Computer Science 2024-10-17 Jingming Zhuo , Songyang Zhang , Xinyu Fang , Haodong Duan , Dahua Lin , Kai Chen

Many evaluation measures are used to evaluate social biases in masked language models (MLMs). However, we find that these previously proposed evaluation measures are lacking robustness in scenarios with limited datasets. This is because…

Computation and Language · Computer Science 2024-01-23 Yang Liu

Survey research faces mounting structural challenges: declining response rates, sample bias, block-wise missingness among at-risk respondents, and AI-assisted fraudulent completions in online panels. Large language models (LLMs) have been…

Artificial Intelligence · Computer Science 2026-05-20 Yan Wang , Ziyi Guo , Christopher McCarty
‹ Prev 1 8 9 10 Next ›