English
Related papers

Related papers: Drawing Conclusions from Draws: Rethinking Prefere…

200 papers

In Natural Language Processing (NLP), the Elo rating system, originally designed for ranking players in dynamic games such as chess, is increasingly being used to evaluate Large Language Models (LLMs) through "A vs B" paired comparisons.…

Computation and Language · Computer Science 2023-11-30 Meriem Boubdir , Edward Kim , Beyza Ermis , Sara Hooker , Marzieh Fadaee

Evaluation has traditionally focused on ranking candidates for a specific skill. Modern generalist models, such as Large Language Models (LLMs), decidedly outpace this paradigm. Open-ended evaluation systems, where candidate models are…

Computer Science and Game Theory · Computer Science 2025-05-09 Siqi Liu , Ian Gemp , Luke Marris , Georgios Piliouras , Nicolas Heess , Marc Lanctot

We introduce LLM CHESS, an evaluation framework designed to probe the generalization of reasoning and instruction-following abilities in large language models (LLMs) through extended agentic interaction in the domain of chess. We rank over…

Artificial Intelligence · Computer Science 2025-12-02 Sai Kolasani , Maxim Saplin , Nicholas Crispino , Kyle Montgomery , Jared Quincy Davis , Matei Zaharia , Chi Wang , Chenguang Wang

Arena-based evaluation is a fundamental yet significant evaluation paradigm for modern AI models, especially large language models (LLMs). Existing framework based on ELO rating system suffers from the inevitable instability problem due to…

Artificial Intelligence · Computer Science 2025-05-30 Zirui Liu , Jiatong Li , Yan Zhuang , Qi Liu , Shuanghong Shen , Jie Ouyang , Mingyue Cheng , Shijin Wang

As large language models (LLMs) continue to advance, accurately and comprehensively evaluating their performance becomes increasingly challenging. Ranking the relative performance of LLMs based on Elo ratings, according to human judgment,…

Computation and Language · Computer Science 2023-11-14 Minghao Wu , Alham Fikri Aji

This work is concerned with the rating of players/teams in face-to-face games with three possible outcomes: loss, win, and draw. This is one of the fundamental problems in sport analytics, where the very simple and popular, non-trivial…

Statistics Theory · Mathematics 2019-10-15 Leszek Szczecinski , Aymen Djebbi

New large language models (LLMs) are being released every day. Some perform significantly better or worse than expected given their parameter count. Therefore, there is a need for a method to independently evaluate models. The current best…

Artificial Intelligence · Computer Science 2025-09-30 Ashwin Ramaswamy , Nestor Demeure , Ermal Rrapaj

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

Assessing the effectiveness of large language models (LLMs) presents substantial challenges. The method of conducting human-annotated battles in an online Chatbot Arena is a highly effective evaluative technique. However, this approach is…

Computation and Language · Computer Science 2024-07-16 Haipeng Luo , Qingfeng Sun , Can Xu , Pu Zhao , Qingwei Lin , Jianguang Lou , Shifeng Chen , Yansong Tang , Weizhu Chen

As Large Language Models (LLMs) expand across domains, LLM judges have become essential for systems evaluation. Current benchmarks typically compare system outputs against baselines. This baseline-mediated approach, though convenient,…

Computation and Language · Computer Science 2025-10-29 Seonil Son , Ju-Min Oh , Heegon Jin , Cheolhun Jang , Jeongbeom Jeong , Kuntae Kim

Large language models perform surprisingly well on many zero-shot classification tasks, but are difficult to fairly compare to supervised classifiers due to the lack of a modifiable decision boundary. In this work, we propose and evaluate a…

Computation and Language · Computer Science 2025-11-25 WonJin Yoon , Ian Bulovic , Timothy A. Miller

Offline evaluation of search systems depends on test collections. These benchmarks provide the researchers with a corpus of documents, topics and relevance judgements indicating which documents are relevant for each topic. While test…

Information Retrieval · Computer Science 2025-07-23 David Otero , Javier Parapar , Álvaro Barreiro

Large Language Models (LLMs) have shown to be effective evaluators across various domains such as machine translations or the scientific domain. Current LLM-as-a-Judge approaches rely mostly on individual assessments or a single round of…

Computation and Language · Computer Science 2025-07-10 Isik Baran Sandan , Tu Anh Dinh , Jan Niehues

Nowadays, the quality of responses generated by different modern large language models (LLMs) is hard to evaluate and compare automatically. Recent studies suggest and predominantly use LLMs for reference-free evaluation of open-ended…

Computation and Language · Computer Science 2025-01-03 Ruosen Li , Teerth Patel , Xinya Du

Preference alignment in Large Language Models (LLMs) has significantly improved their ability to adhere to human instructions and intentions. However, existing direct alignment algorithms primarily focus on relative preferences and often…

Machine Learning · Computer Science 2025-05-13 Shenao Zhang , Zhihan Liu , Boyi Liu , Yufeng Zhang , Yingxiang Yang , Yongfei Liu , Liyu Chen , Tao Sun , Zhaoran Wang

Search-augmented language models combine web search with Large Language Models (LLMs) to improve response groundedness and freshness. However, analyzing these systems remains challenging: existing datasets are limited in scale and narrow in…

Large Language Models (LLMs) excel at linear reasoning tasks but remain underexplored on non-linear structures such as those found in natural debates, which are best expressed as argument graphs. We evaluate whether LLMs can approximate…

Computation and Language · Computer Science 2025-09-22 Reza Sanayei , Srdjan Vesic , Eduardo Blanco , Mihai Surdeanu

Deciding which large language model (LLM) to use is a complex challenge. Pairwise ranking has emerged as a new method for evaluating human preferences for LLMs. This approach entails humans evaluating pairs of model outputs based on a…

Computation and Language · Computer Science 2025-02-18 Roland Daynauth , Christopher Clarke , Krisztian Flautner , Lingjia Tang , Jason Mars

Reward model (RM) plays a pivotal role in reinforcement learning with human feedback (RLHF) for aligning large language models (LLMs). However, classical RMs trained on human preferences are vulnerable to reward hacking and generalize…

Machine Learning · Computer Science 2025-10-24 Zhenghao Xu , Qin Lu , Qingru Zhang , Liang Qiu , Ilgee Hong , Changlong Yu , Wenlin Yao , Yao Liu , Haoming Jiang , Lihong Li , Hyokun Yun , Tuo Zhao

Recent studies have demonstrated that large language models (LLMs) exhibit significant biases in evaluation tasks, particularly in preferentially rating and favoring self-generated content. However, the extent to which this bias manifests…

Computation and Language · Computer Science 2025-12-09 Yen-Shan Chen , Jing Jin , Peng-Ting Kuo , Chao-Wei Huang , Yun-Nung Chen
‹ Prev 1 2 3 10 Next ›