English
Related papers

Related papers: The Base-Rate Effect on LLM Benchmark Performance:…

200 papers

The discrepancy between maximum likelihood estimation (MLE) and task measures such as BLEU score has been studied before for autoregressive neural machine translation (NMT) and resulted in alternative training algorithms (Ranzato et al.,…

Computation and Language · Computer Science 2021-09-22 Sumanta Bhattacharyya , Amirmohammad Rooshenas , Subhajit Naskar , Simeng Sun , Mohit Iyyer , Andrew McCallum

Reinforcement learning from human feedback (RLHF) and, at its core, reward modeling have become a crucial part of training powerful large language models (LLMs). One commonly overlooked factor in training high-quality reward models (RMs) is…

Computation and Language · Computer Science 2025-05-19 Kian Ahrabian , Pegah Jandaghi , Negar Mokhberian , Sai Praneeth Karimireddy , Jay Pujara

The Mutual Reinforcement Effect (MRE) investigates the synergistic relationship between word-level and text-level classifications in text classification tasks. It posits that the performance of both classification levels can be mutually…

Computation and Language · Computer Science 2024-10-15 Chengguang Gan , Tatsunori Mori

This paper investigates the ability of large language models (LLMs) to solve statistical tasks, as well as their capacity to assess the quality of reasoning. While state-of-the-art LLMs have demonstrated remarkable performance in a range of…

Computation and Language · Computer Science 2026-01-22 Crish Nagarkar , Leonid Bogachev , Serge Sharoff

Despite its importance to experimental design, statistical power (the probability that, given a real effect, an experiment will reject the null hypothesis) has largely been ignored by the NLP community. Underpowered experiments make it more…

Computation and Language · Computer Science 2020-10-15 Dallas Card , Peter Henderson , Urvashi Khandelwal , Robin Jia , Kyle Mahowald , Dan Jurafsky

Large Language Models (LLMs) can achieve inflated scores on multiple-choice tasks by exploiting inherent biases in option positions or labels, rather than demonstrating genuine understanding. This study introduces SCOPE, an evaluation…

Computation and Language · Computer Science 2025-08-05 Wonjun Jeong , Dongseok Kim , Taegkeun Whangbo

We study online preference-based reinforcement learning (PbRL) with the goal of improving sample efficiency. While a growing body of theoretical work has emerged-motivated by PbRL's recent empirical success, particularly in aligning large…

Machine Learning · Computer Science 2026-02-06 Joongkyu Lee , Seouh-won Yi , Min-hwan Oh

Benchmarks have emerged as the central approach for evaluating Large Language Models (LLMs). The research community often relies on a model's average performance across the test prompts of a benchmark to evaluate the model's performance.…

Computation and Language · Computer Science 2024-06-07 Melissa Ailem , Katerina Marazopoulou , Charlotte Siska , James Bono

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

Although recent Massively Multilingual Language Models (MMLMs) like mBERT and XLMR support around 100 languages, most existing multilingual NLP benchmarks provide evaluation data in only a handful of these languages with little linguistic…

Computation and Language · Computer Science 2022-11-15 Kabir Ahuja , Sandipan Dandapat , Sunayana Sitaram , Monojit Choudhury

Benchmarks underpin how progress in large language models (LLMs) is measured and trusted. Yet our analyses reveal that apparent convergence in benchmark accuracy can conceal deep epistemic divergence. Using two major reasoning benchmarks -…

Computation and Language · Computer Science 2026-02-13 Eddie Yang , Dashun Wang

Applying Reinforcement learning (RL) following maximum likelihood estimation (MLE) pre-training is a versatile method for enhancing neural machine translation (NMT) performance. However, recent work has argued that the gains produced by RL…

Computation and Language · Computer Science 2022-10-07 Asaf Yehudai , Leshem Choshen , Lior Fox , Omri Abend

As large language models (LLMs) have grown in prevalence, particular benchmarks have become essential for the evaluation of these models and for understanding model capabilities. Most commonly, we use test accuracy averaged across multiple…

Computation and Language · Computer Science 2024-11-12 Vipul Gupta , David Pantoja , Candace Ross , Adina Williams , Megan Ung

LLMs have demonstrated impressive zero-shot performance on NLP tasks thanks to the knowledge they acquired in their training. In multiple-choice QA tasks, the LM probabilities are used as an imperfect measure of the plausibility of each…

Computation and Language · Computer Science 2023-11-06 Wenkai Chen , Sahithya Ravi , Vered Shwartz

Large language models (LLMs) excel on multiple-choice clinical diagnosis benchmarks, yet it is unclear how much of this performance reflects underlying probabilistic reasoning. We study this through questions from MedQA, where the task is…

Computation and Language · Computer Science 2025-12-16 Furong Jia , Yuan Pu , Finn Guo , Monica Agrawal

The natural language understanding (NLU) performance of large language models (LLMs) has been evaluated across various tasks and datasets. The existing evaluation methods, however, do not take into account the variance in scores due to…

Computation and Language · Computer Science 2024-08-23 Yusuke Sakai , Adam Nohejl , Jiangnan Hang , Hidetaka Kamigaito , Taro Watanabe

In the Bayesian Reinforcement Learning (BRL) setting, agents try to maximise the collected rewards while interacting with their environment while using some prior knowledge that is accessed beforehand. Many BRL algorithms have already been…

Artificial Intelligence · Computer Science 2016-09-28 Michael Castronovo , Damien Ernst , Adrien Couetoux , Raphael Fonteneau

The ability to rigorously estimate the failure rates of large language models (LLMs) is a prerequisite for their safe deployment. Currently, however, practitioners often face a tradeoff between expensive human gold standards and potentially…

Computation and Language · Computer Science 2026-04-07 Minghe Shen , Ananth Balashankar , Adam Fisch , David Madras , Miguel Rodrigues

The performance of Large Language Models (LLMs) on downstream tasks is fundamentally constrained by the capabilities acquired during pre-training. However, traditional benchmarks like MMLU often fail to reflect a base model's plasticity in…

Computation and Language · Computer Science 2026-05-13 Xiaoyuan Li , Yubo Ma , Kexin Yang , Moxin Li , Keqin Bao , Wenie Wang , Fuli Feng , Dayiheng Liu

Scaling pre-training compute has proven effective for achieving mulitlinguality, but does the same hold for test-time scaling? In this work, we introduce MCLM, a multilingual math benchmark featuring competition-level problems in 55…

Computation and Language · Computer Science 2025-08-04 Guijin Son , Jiwoo Hong , Hyunwoo Ko , James Thorne
‹ Prev 1 2 3 10 Next ›