REVIEW 19 cited by
Evaluating Large Language Models: A Comprehensive Survey
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Large language models (LLMs) have demonstrated remarkable capabilities across a broad spectrum of tasks. They have attracted significant attention and been deployed in numerous downstream applications. Nevertheless, akin to a double-edged sword, LLMs also present potential risks. They could suffer from private data leaks or yield inappropriate, harmful, or misleading content. Additionally, the rapid progress of LLMs raises concerns about the potential emergence of superintelligent systems without adequate safeguards. To effectively capitalize on LLM capacities as well as ensure their safe and beneficial development, it is critical to conduct a rigorous and comprehensive evaluation of LLMs. This survey endeavors to offer a panoramic perspective on the evaluation of LLMs. We categorize the evaluation of LLMs into three major groups: knowledge and capability evaluation, alignment evaluation and safety evaluation. In addition to the comprehensive review on the evaluation methodologies and benchmarks on these three aspects, we collate a compendium of evaluations pertaining to LLMs' performance in specialized domains, and discuss the construction of comprehensive evaluation platforms that cover LLM evaluations on capabilities, alignment, safety, and applicability. We hope that this comprehensive overview will stimulate further research interests in the evaluation of LLMs, with the ultimate goal of making evaluation serve as a cornerstone in guiding the responsible development of LLMs. We envision that this will channel their evolution into a direction that maximizes societal benefit while minimizing potential risks. A curated list of related papers has been publicly available at https://github.com/tjunlp-lab/Awesome-LLMs-Evaluation-Papers.
Forward citations
Cited by 19 Pith papers
-
BabelJudge: Measuring LLM-as-a-Judge Reliability Across Languages and Agent Trajectories
BabelJudge introduces a perturbation-based framework to audit LLM judges for position bias, verbosity bias, order inconsistency, and cross-lingual degradation without human preference labels.
-
Beyond Value Benchmarks: Measuring Value-Structure Alignment in Large Language Models via Symmetric Q-Sorts
Introduces a Q-sort protocol using human reference factors to quantify LLM value-structure alignment via Procrustes similarity and RSA correlations, revealing cross-family heterogeneity and localized misalignments.
-
PatientAgentBench: A Benchmark Framework for Evaluating Patient-Facing Health AI Agents
A clinician-validated benchmark for patient-facing health AI agents shows that even frontier models fail triage in up to a quarter of realistic tool-using conversations.
-
A Unified Perturbation Framework for Analyzing Leaderboard Stability and Manipulation
A perturbation framework with Drop/Add/Flip and player-removal operations demonstrates that Bradley-Terry leaderboards are non-robust to sub-1% targeted changes that alter top ranks, Kendall tau, and confidence intervals.
-
Do Language Models Encode Knowledge of Linguistic Constraint Violations?
Sparse autoencoder features in language models do not satisfy joint falsification criteria for unified grammatical violation detectors across linguistic phenomena.
-
Do Language Models Encode Knowledge of Linguistic Constraint Violations?
Sparse autoencoder analysis of language model activations finds limited evidence for a unified set of features detecting linguistic constraint violations.
-
The Generalized Turing Test: A Foundation for Comparing Intelligence
The Generalized Turing Test defines relative intelligence as the inability of one agent to distinguish an imitator from the original through interaction.
-
When LLM Judges Inflate Scores: Exploring Overrating in Relevance Assessment
LLMs consistently overrate relevance of inadequate passages in IR evaluations due to biases toward length and lexical features rather than true content match.
-
Encouraging Good Processes Without the Need for Good Answers: Reinforcement Learning for LLM Agent Planning
Decoupling LLM-agent planning from summarization and rewarding tool-call completeness rather than final-answer correctness improves planning by 8-12% and end-to-end answers by 5-6% over end-to-end RL baselines.
-
SKA-Bench: A Fine-Grained Benchmark for Evaluating Structured Knowledge Understanding of LLMs
SKA-Bench is a fine-grained QA benchmark across KG, table, and hybrid formats that shows current LLMs remain sensitive to noise and order and often hallucinate instead of rejecting unanswerable inputs.
-
Efficient Sequential Evaluation of Large Language Models
A confidence-sequence framework for sequentially estimating an LLM's average benchmark accuracy under adaptive question selection, with growth-oriented sampling rules that in practice often lose to uniform sampling.
-
Beyond "I cannot fulfill this request": Alleviating Rigid Rejection in LLMs via Label Enhancement
LANCE applies variational inference for label enhancement across multiple rejection categories, supplying gradients to a refinement model that produces safe, non-rigid responses from LLMs.
-
User Behavior Prediction as a Generic, Robust, Scalable, and Low-Cost Evaluation Strategy for Estimating Generalization in LLMs
The authors introduce an entropy-based framework that uses user behavior prediction as a measure of LLM generalization, and find GPT-4o outperforms GPT-4o-mini and Llama-3.1 on movie and music recommendation tasks.
-
Multiple Choice Questions: Reasoning Makes Large Language Models (LLMs) More Self-Confident, Especially When They are Wrong
Reasoning before answering MCQs increases LLM confidence more for incorrect answers and degrades calibration on a 57-subject benchmark across seven models.
-
Cognitive Agents Powered by Large Language Models for Agile Software Project Management
LLM agents acting as Agile roles produced plausible project artifacts in simulation, but the claimed improvements over human teams are unsupported because no comparison or validated metrics are provided.
-
OpenFActScore: Open-Source Atomic Evaluation of Factuality in Text Generation
Using Olmo to extract atomic facts and Gemma to verify them against Wikipedia, OpenFActScore reproduces the original FActScore ranking of 10 LLMs with a Pearson correlation above 0.99.
-
Software Engineering for Large Language Models: Research Status, Challenges and the Road Ahead
A literature review organizes LLM development into a six-phase software engineering lifecycle and identifies challenges and research directions for each phase.
-
LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods
A survey that organizes LLMs-as-judges research into functionality, methodology, applications, meta-evaluation, and limitations.
-
A Survey on the Memory Mechanism of Large Language Model based Agents
A systematic review of memory designs, evaluation methods, applications, limitations, and future directions for LLM-based agents.
Discussion (0). Sign in to comment.