English
Related papers

Related papers: SEAL: Can Saturated Benchmarks Be Revived by LLM-a…

200 papers

Large Language Models (LLMs) have achieved remarkable capabilities, yet their improvement methods remain fundamentally constrained by human design. We present Self-Developing, a framework that enables LLMs to autonomously discover,…

Computation and Language · Computer Science 2025-06-11 Yoichi Ishibashi , Taro Yano , Masafumi Oyamada

Excel is a pervasive yet often complex tool, particularly for novice users, where runtime errors arising from logical mistakes or misinterpretations of functions pose a significant challenge. While large language models (LLMs) offer…

The "LLM-as-a-Judge" paradigm, using Large Language Models (LLMs) as automated evaluators, is pivotal to LLM development, offering scalable feedback for complex tasks. However, the reliability of these judges is compromised by various…

Computation and Language · Computer Science 2026-05-22 Qingquan Li , Shaoyu Dou , Kailai Shao , Chao Chen , Haixiang Hu

Large language models (LLMs) are evolving fast and are now frequently used as evaluators, in a process typically referred to as LLM-as-a-Judge, which provides quality assessments of model outputs. However, recent research points out…

Computation and Language · Computer Science 2026-01-27 Hugo Silva , Mateus Mendes , Hugo Gonçalo Oliveira

To reduce the need for human annotations, large language models (LLMs) have been proposed as judges of the quality of other candidate models. The performance of LLM judges is typically evaluated by measuring the correlation with human…

Computation and Language · Computer Science 2025-05-14 Andreas Stephan , Dawei Zhu , Matthias Aßenmacher , Xiaoyu Shen , Benjamin Roth

Multimodal Large Language Models (MLLMs) have gained significant attention recently, showing remarkable potential in artificial general intelligence. However, assessing the utility of MLLMs presents considerable challenges, primarily due to…

Computation and Language · Computer Science 2024-06-12 Dongping Chen , Ruoxi Chen , Shilin Zhang , Yinuo Liu , Yaochen Wang , Huichi Zhou , Qihui Zhang , Yao Wan , Pan Zhou , Lichao Sun

Benchmarks are important tools to track progress in the development of Large Language Models (LLMs), yet inaccuracies in datasets and evaluation methods consistently undermine their effectiveness. Here, we present Omni-MATH-2, a manually…

Artificial Intelligence · Computer Science 2026-01-28 Marthe Ballon , Andres Algaba , Brecht Verbeken , Vincent Ginis

Large language models (LLMs) are systematically overconfident: they routinely express high certainty on questions they often answer incorrectly. Existing calibration methods either require labeled validation data, degrade under distribution…

Computation and Language · Computer Science 2026-04-14 Mohamed Rissal Hedna , Jan Strich , Martin Semmann , Chris Biemann

Adaptive prompt and program search makes LLM evaluation selection-sensitive. Once benchmark items are reused inside tuning, the observed winner's score need not estimate the fresh-data performance of the full tune-then-deploy procedure. We…

Machine Learning · Statistics 2026-05-08 Yang Xu , Jiefu Zhang , Haixiang Sun , Zihan Zhou , Tianyu Cao , Vaneet Aggarwal

Benchmarks and leaderboards are how NLP most often communicates progress, but in the LLM era they are increasingly easy to misread. Scores can reflect benchmark-chasing, hidden evaluation choices, or accidental exposure to test content --…

Artificial Intelligence · Computer Science 2026-03-25 Jan Christian Blaise Cruz , Alham Fikri Aji

Assessment and evaluation have long been critical challenges in artificial intelligence (AI) and natural language processing (NLP). Traditional methods, usually matching-based or small model-based, often fall short in open-ended and dynamic…

As large language models (LLMs) continue to scale up, their performance on various downstream tasks has significantly improved. However, evaluating their capabilities has become increasingly expensive, as performing inference on a large…

Computation and Language · Computer Science 2026-02-10 Taolin Zhang , Hang Guo , Wang Lu , Tao Dai , Shu-Tao Xia , Jindong Wang

As interactive LLM-based applications are created and refined, model developers need to evaluate the quality of generated text along many possible axes. For simpler systems, human evaluation may be practical, but in complicated systems like…

Computation and Language · Computer Science 2026-05-22 Zhenwei Tang , Zhaoyan Liu , Rasa Hosseinzadeh , Tongzi Wu , Keyvan Golestan , Jesse C. Cresswell

Large Language Models (LLMs), such as OpenAI's o1-series have demonstrated compelling capabilities for complex reasoning tasks via the extended chain-of-thought (CoT) reasoning mechanism. However, recent studies reveal substantial…

Computation and Language · Computer Science 2025-10-28 Runjin Chen , Zhenyu Zhang , Junyuan Hong , Souvik Kundu , Zhangyang Wang

We introduce Debate Speech Evaluation as a novel and challenging benchmark for assessing LLM judges. Evaluating debate speeches requires a deep understanding of the speech at multiple levels, including argument strength and relevance, the…

Computation and Language · Computer Science 2025-09-10 Noy Sternlicht , Ariel Gera , Roy Bar-Haim , Tom Hope , Noam Slonim

Recent advances have demonstrated the effectiveness of Reinforcement Learning (RL) in improving the reasoning capabilities of Large Language Models (LLMs). However, existing works inevitably rely on high-quality instructions and verifiable…

Computation and Language · Computer Science 2026-01-27 Wenkai Fang , Shunyu Liu , Yang Zhou , Kongcheng Zhang , Tongya Zheng , Kaixuan Chen , Mingli Song , Dacheng Tao

The reliability of multilingual Large Language Model (LLM) evaluation is currently compromised by the inconsistent quality of translated benchmarks. Existing resources often suffer from semantic drift and context loss, which can lead to…

Computation and Language · Computer Science 2026-02-26 Hanna Yukhymenko , Anton Alexandrov , Martin Vechev

The evaluation of Large Language Models (LLMs) increasingly relies on other LLMs acting as judges. However, current evaluation paradigms typically yield a single score or ranking, answering which model is better but not why. While essential…

Computation and Language · Computer Science 2025-07-25 Asaf Yehudai , Lilach Eden , Yotam Perlitz , Roy Bar-Haim , Michal Shmueli-Scheuer

As frontier Large Language Models (LLMs) increasingly saturate new benchmarks shortly after they are published, benchmarking itself is at a juncture: if frontier models keep improving, it will become increasingly hard for humans to generate…

Automatic evaluation with large language models, commonly known as LLM-as-a-judge, is now standard across reasoning and alignment tasks. Despite evaluating many samples in deployment, these evaluators typically (i) treat each case…

Computation and Language · Computer Science 2025-12-09 Seungyeon Jwa , Daechul Ahn , Reokyoung Kim , Dongyeop Kang , Jonghyun Choi