相关论文: am-ELO: A Stable Framework for Arena-based LLM Eva…

Measuring innovation often relies on context-specific proxies and on expert evaluation. Hence, empirical innovation research is often limited to settings where such data is available. We investigate how large language models (LLMs) can be…

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…

Designing effective reward functions remains a fundamental challenge in reinforcement learning (RL), as it often requires extensive human effort and domain expertise. While RL from human feedback has been successful in aligning agents with…

Progress in AI is often demonstrated by new models claiming improved performance on tasks measuring model capabilities. Evaluating language models can be particularly challenging, as choices of how a model is evaluated on a task can lead to…

Existing evaluation of Large Language Models (LLMs) on static benchmarks is vulnerable to data contamination and leaderboard overfitting, critical issues that obscure true model capabilities. To address this, we introduce LLMEval-Fair, a…

Many existing evaluation benchmarks for Large Language Models (LLMs) quickly become outdated due to the emergence of new models and training data. These benchmarks also fall short in assessing how LLM performance changes over time, as they…

Existing benchmarks for large multimodal models (LMMs) often fail to capture their performance in real-time, adversarial environments. We introduce LM Fight Arena (Large Model Fight Arena), a novel framework that evaluates LMMs by pitting…

As Large Language Models (LLMs) become increasingly integrated into real-world, autonomous applications, relying on static, pre-annotated references for evaluation poses significant challenges in cost, scalability, and completeness. We…

Self-evaluation, a model's ability to assess the correctness of its own output, is crucial for Large Multimodal Models (LMMs) to achieve self-improvement in multi-turn conversations, yet largely absent in foundation models. Recent work has…

Despite their sophisticated capabilities, large language models (LLMs) encounter a major hurdle in effective assessment. This paper first revisits the prevalent evaluation method-multiple choice question answering (MCQA), which allows for…

Large language models (LLMs) have recently emerged as promising tools for solving challenging robotic tasks, even in the presence of action and observation uncertainties. Recent LLM-based decision-making methods (also referred to as…

Evaluation of large language models (LLMs) is increasingly critical, yet standard benchmarking methods rely on average accuracy, overlooking both the inherent stochasticity of LLM outputs and the heterogeneity of benchmark items. Item…

Reviewer assignment is increasingly critical yet challenging in the LLM era, where rapid topic shifts render many pre-2023 benchmarks outdated and where proxy signals poorly reflect true reviewer familiarity. We address this evaluation…

Reinforcement Learning (RL) has enabled Large Language Models (LLMs) to acquire increasingly complex reasoning and agentic behaviors. In this work, we propose two simple techniques to improve policy gradient algorithms for LLMs. First, we…

Traditional retrieval-augmented generation (RAG) benchmarks evaluate systems using heuristic-based metrics, but these require human preferences as the ground truth for reference. In contrast, arena-based benchmarks, where systems compete…

Model-based reinforcement learning (RL) is considered to be a promising approach to reduce the sample complexity that hinders model-free RL. However, the theoretical understanding of such methods has been rather limited. This paper…

Large-language-model (LLM) agents exhibit complex, context-sensitive behaviour that quickly renders static benchmarks and ad-hoc manual testing obsolete. We present Neo, a configurable, multi-agent framework that automates realistic,…

This paper presents an Elo-based rating system for programming contests, specifically Topcoder's Single Round Matches (SRMs). We introduce a logarithmic rank-based performance metric that allows single-round, multi-player contest results to…

Evaluating the quality of arguments is a crucial aspect of any system leveraging argument mining. However, it is a challenge to obtain reliable and consistent annotations regarding argument quality, as this usually requires domain-specific…

Alignment of large language models (LLMs) typically involves training a reward model on preference data, followed by policy optimization with respect to the reward model. However, optimizing policies with respect to a single reward model…