A Survey on Evaluation of Large Language Models
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:SM2TNWV4record.jsonopen to challenge →
read the original abstract
Large language models (LLMs) are gaining increasing popularity in both academia and industry, owing to their unprecedented performance in various applications. As LLMs continue to play a vital role in both research and daily use, their evaluation becomes increasingly critical, not only at the task level, but also at the society level for better understanding of their potential risks. Over the past years, significant efforts have been made to examine LLMs from various perspectives. This paper presents a comprehensive review of these evaluation methods for LLMs, focusing on three key dimensions: what to evaluate, where to evaluate, and how to evaluate. Firstly, we provide an overview from the perspective of evaluation tasks, encompassing general natural language processing tasks, reasoning, medical usage, ethics, educations, natural and social sciences, agent applications, and other areas. Secondly, we answer the `where' and `how' questions by diving into the evaluation methods and benchmarks, which serve as crucial components in assessing performance of LLMs. Then, we summarize the success and failure cases of LLMs in different tasks. Finally, we shed light on several future challenges that lie ahead in LLMs evaluation. Our aim is to offer invaluable insights to researchers in the realm of LLMs evaluation, thereby aiding the development of more proficient LLMs. Our key point is that evaluation should be treated as an essential discipline to better assist the development of LLMs. We consistently maintain the related open-source materials at: https://github.com/MLGroupJLU/LLM-eval-survey.
This paper has not been read by Pith yet.
Forward citations
Cited by 23 Pith papers
-
From Text to Voice: A Reproducible and Verifiable Framework for Evaluating Tool Calling LLM Agents
A dataset-agnostic framework converts text tool-calling benchmarks to paired audio versions via TTS and noise, showing model-dependent performance with small text-to-voice gaps of 1.8-4.8 points on Confetti and When2Call.
-
LLM Agents for Deliberative Collaboration: A Study on Joint Decision Making Under Partial Observability
A benchmark for LLM agents in partially observable joint decision-making reveals that deliberation challenges current models but can enable reflection and error correction.
-
An Empirical Evaluation of LLM-Generated Code Security Across Prompting Methods
Empirical study across five LLMs and four languages finds security-aware prompting changes CWE category distributions but yields no statistically significant reduction in vulnerability frequency or density.
-
From Text to Voice: A Reproducible and Verifiable Framework for Evaluating Tool Calling LLM Agents
A dataset-agnostic framework converts text tool-calling benchmarks to paired audio evaluations via TTS, speaker variation and noise, then evaluates seven omni-modal models showing model- and task-dependent performance...
-
Conditional Attribute Estimation with Autoregressive Sequence Models
Conditional Attribute Transformers jointly estimate next-token probabilities and conditional attribute values for autoregressive sequence models, enabling credit assignment, counterfactuals, and steerable generation i...
-
Pop Quiz Attack: Black-box Membership Inference Attacks Against Large Language Models
PopQuiz Attack infers LLM training data membership by turning examples into quiz questions and measuring answer accuracy, reaching 0.873 average ROC-AUC across six models and outperforming prior methods by 20.6%.
-
Reward-Decomposed Reinforcement Learning for Immersive Video Role-Playing
EBM-RL decomposes reinforcement learning into perception-think-answer stages with CLIP alignment, perceptual-cognitive, accuracy, and format rewards to improve immersive video role-playing over text baselines.
-
Reward-Decomposed Reinforcement Learning for Immersive Video Role-Playing
EBM-RL applies a GRPO-based RL method with decomposed rewards for scene alignment, perceptual utility, faithfulness, and format to improve video-grounded role-playing dialogue over text-only baselines.
-
Compared to What? Baselines and Metrics for Counterfactual Prompting
Counterfactual prompting effects on LLMs are often indistinguishable from those caused by meaning-preserving paraphrases, causing most previously reported demographic sensitivities to disappear under proper statistica...
-
Measuring Representation Robustness in Large Language Models for Geometry
LLMs display accuracy gaps of up to 14 percentage points on the same geometry problems solely due to representation choice, with vector forms consistently weakest and a convert-then-solve prompt helping only high-capa...
-
ALL-FEM: Agentic Large Language models Fine-tuned for Finite Element Methods
ALL-FEM fine-tunes LLMs on a corpus of verified FEniCS scripts and uses multi-agent workflows to automate finite element code generation, achieving 71.79% success on 39 benchmarks across elasticity, flow, and coupled ...
-
LLMEval-Fair: A Large-Scale Longitudinal Study on Robust and Fair Evaluation of Large Language Models
LLMEval-Fair introduces a dynamic, contamination-resistant evaluation framework for LLMs based on a large question bank and validates it via a 30-month study of nearly 60 models showing performance ceilings and hidden...
-
Primus: Enforcing Attention Usage for 3D Medical Image Segmentation
Primus and PrimusV2 are Transformer-centric models that match or exceed nnU-Net and top CNNs on nine 3D medical segmentation datasets by enforcing attention usage.
-
When AI Says It Feels
LLMs trained via rubric-based self-rewarding RL with GRPO enhanced feeling expression and sycophancy robustness but degraded truthful QA performance.
-
Heterogeneous Scientific Foundation Model Collaboration
Eywa enables language-based agentic AI systems to collaborate with specialized scientific foundation models for improved performance on structured data tasks.
-
STELLAR-E: a Synthetic, Tailored, End-to-end LLM Application Rigorous Evaluator
STELLAR-E modifies the TGRT Self-Instruct framework to produce tailored synthetic LLM evaluation datasets that score an average 5.7% higher on LLM-as-a-judge metrics than existing language-specific benchmarks.
-
Empirical Evidence of Complexity-Induced Limits in Large Language Models on Finite Discrete State-Space Problems with Explicit Validity Constraints
Large reasoning models exhibit reasoning collapse, with accuracy dropping sharply beyond task-specific complexity thresholds in controlled versions of nine classical reasoning tasks using strict validity validators.
-
A Graph-Enhanced Defense Framework for Explainable Fake News Detection with LLM
G-Defense builds claim-centered graphs from sub-claims, applies RAG for evidence and competing explanations, then uses graph inference to detect fake news veracity and generate intuitive explanation graphs, claiming S...
-
The Role of Emotional Stimuli and Intensity in Shaping Large Language Model Behavior
Positive emotional prompts improve LLM accuracy and reduce toxicity but increase sycophantic agreement, while negative emotions show the reverse pattern.
-
Instruction-Following Evaluation for Large Language Models
IFEval is a new benchmark of 25 verifiable instruction types and ~500 prompts for objective, reproducible evaluation of LLMs' instruction-following abilities.
-
What makes a harness a harness: necessary and sufficient conditions for an agent harness
Proposes and tests a constitutive definition of 'agent harness' via conceptual analysis of literature and six real systems.
-
Sensorimotor Self-Recognition in Multimodal Large Language Model-Driven Robots
Multimodal LLMs in robots develop self-identification and predictive awareness through sensorimotor loops, with structural equation modeling linking sensory integration to dimensions of the minimal self.
-
Data-Centric Foundation Models in Computational Healthcare: A Survey
The paper surveys data-centric strategies for foundation models in computational healthcare and supplies a curated list of related models and datasets.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.