English
Related papers

Related papers: Signal and Noise: A Framework for Reducing Uncerta…

200 papers

We propose a simulation framework for generating instance-dependent noisy labels via a pseudo-labeling paradigm. We show that the distribution of the synthetic noisy labels generated with our framework is closer to human labels compared to…

Machine Learning · Computer Science 2021-10-19 Keren Gu , Xander Masotto , Vandana Bachani , Balaji Lakshminarayanan , Jack Nikodem , Dong Yin

The emergence of powerful LLMs has led to a paradigm shift in Natural Language Understanding and Natural Language Generation. The properties that make LLMs so valuable for these tasks -- creativity, ability to produce fluent speech, and…

Computation and Language · Computer Science 2025-03-10 Kelsey Kraus , Margaret Kroll

Large Language Models (LLMs) effectiveness is usually evaluated by means of benchmarks such as MMLU, ARC-C, or HellaSwag, where questions are presented in their original wording, thus in a fixed, standardized format. However, real-world…

Computation and Language · Computer Science 2025-09-05 Riccardo Lunardi , Vincenzo Della Mea , Stefano Mizzaro , Kevin Roitero

The breakthrough of generative large language models (LLMs) that can solve different tasks through chat interaction has led to a significant increase in the use of general benchmarks to assess the quality or performance of these models…

Computation and Language · Computer Science 2025-04-03 Fabio Barth , Georg Rehm

We conduct a systematic audit of three widely used reasoning benchmarks, SocialIQa, FauxPas-EAI, and ToMi, and uncover pervasive flaws in both benchmark items and evaluation methodology. Using five LLMs (GPT-{3, 3.5, 4, o1}, and LLaMA 3.1)…

Computation and Language · Computer Science 2025-07-01 Seyed Mahed Mousavi , Edoardo Cecchinato , Lucia Hornikova , Giuseppe Riccardi

Large language model (LLM) evaluation is increasingly costly, prompting interest in methods that speed up evaluation by shrinking benchmark datasets. Benchmark prediction (also called efficient LLM evaluation) aims to select a small subset…

Machine Learning · Computer Science 2025-06-10 Guanhua Zhang , Florian E. Dorner , Moritz Hardt

Advances in neural modeling have achieved state-of-the-art (SOTA) results on public natural language processing (NLP) benchmarks, at times surpassing human performance. However, there is a gap between public benchmarks and real-world…

Computation and Language · Computer Science 2023-02-14 Asa Cooper Stickland , Sailik Sengupta , Jason Krone , Saab Mansour , He He

Risk assessment tools are widely used around the country to inform decision making within the criminal justice system. Recently, considerable attention has been devoted to the question of whether such tools may suffer from racial bias. In…

Methodology · Statistics 2020-04-01 Riccardo Fogliato , Max G'Sell , Alexandra Chouldechova

Large language models (LLMs) often produce inaccurate or misleading content-hallucinations. To address this challenge, we introduce Noise-Augmented Fine-Tuning (NoiseFiT), a novel framework that leverages adaptive noise injection based on…

Computation and Language · Computer Science 2025-05-06 Afshin Khadangi , Amir Sartipi , Igor Tchappi , Ramin Bahmani

Large language models (LLMs) are stochastic, and not all models give deterministic answers, even when setting temperature to zero with a fixed random seed. However, few benchmark studies attempt to quantify uncertainty, partly due to the…

Computation and Language · Computer Science 2025-06-30 Robert E. Blackwell , Jon Barry , Anthony G. Cohn

Evaluation benchmarks are the cornerstone of measuring capabilities of large language models (LLMs), as well as driving progress in said capabilities. Originally designed to make claims about capabilities (or lack thereof) in fully…

Effectively finetuning pretrained language models (PLMs) is critical for their success in downstream tasks. However, PLMs may have risks in overfitting the pretraining tasks and data, which usually have gap with the target downstream tasks.…

Computation and Language · Computer Science 2022-03-24 Chuhan Wu , Fangzhao Wu , Tao Qi , Yongfeng Huang , Xing Xie

Reliable certification of Large Language Models (LLMs)-verifying that failure rates are below a safety threshold-is critical yet challenging. While "LLM-as-a-Judge" offers scalability, judge imperfections, noise, and bias can invalidate…

Machine Learning · Computer Science 2026-01-30 Chen Feng , Minghe Shen , Ananth Balashankar , Carsten Gerner-Beuerle , Miguel R. D. Rodrigues

For many real-world applications, the user-generated inputs usually contain various noises due to speech recognition errors caused by linguistic variations1 or typographical errors (typos). Thus, it is crucial to test model performance on…

Computation and Language · Computer Science 2023-05-26 Chenglei Si , Zhengyan Zhang , Yingfa Chen , Xiaozhi Wang , Zhiyuan Liu , Maosong Sun

As language models (LMs) become increasingly powerful and widely used, it is important to quantify them for sociodemographic bias with potential for harm. Prior measures of bias are sensitive to perturbations in the templates designed to…

Computation and Language · Computer Science 2024-08-09 Vipul Gupta , Pranav Narayanan Venkit , Hugo Laurençon , Shomir Wilson , Rebecca J. Passonneau

Prompt optimization algorithms for Large Language Models (LLMs) excel in multi-step reasoning but still lack effective uncertainty estimation. This paper introduces a benchmark dataset to evaluate uncertainty metrics, focusing on Answer,…

Machine Learning · Computer Science 2024-12-30 Pei-Fu Guo , Yun-Da Tsai , Shou-De Lin

As large language models achieve impressive scores on traditional benchmarks, an increasing number of researchers are becoming concerned about benchmark data leakage during pre-training, commonly known as the data contamination problem. To…

Computation and Language · Computer Science 2024-06-27 Kun Qian , Shunji Wan , Claudia Tang , Youzhi Wang , Xuanming Zhang , Maximillian Chen , Zhou Yu

Robust benchmarks are crucial for evaluating Multimodal Large Language Models (MLLMs). Yet we find that models can ace many multimodal benchmarks without strong visual understanding, instead exploiting biases, linguistic priors, and…

Computer Vision and Pattern Recognition · Computer Science 2025-11-07 Ellis Brown , Jihan Yang , Shusheng Yang , Rob Fergus , Saining Xie

Large Language Models (LLMs) are increasingly used to automate classification tasks in business, such as analyzing customer satisfaction from text. However, the inherent stochasticity of LLMs can create measurement error when the outcome is…

Methodology · Statistics 2026-04-24 Yichi Zhang , Ignacio Martinez

Fine-tuning is the dominant paradigm for adapting pretrained large language models (LLMs) to downstream NLP tasks. In practice, fine-tuning datasets may contain various forms of noise arising from annotation errors, preprocessing artifacts,…

Machine Learning · Computer Science 2026-04-15 Lingfang Li , Procheta Sen