LLM Evaluation @ NeurIPS

124 papers126 directions

Papers by Year

2025 124

Top Research Directions

Research directions most represented by papers from this venue.

Evaluating Generative AI with Large Language Models 8
Shifting from Static Benchmarks to Dynamic Evaluation 8
Systematic Biases in Large Language Model Evaluators 6
Factual Inaccuracy and Hallucination in Large Language Models 6
Autonomous Code Refinement via Execution Feedback Loops 3
Granular Verification via Atomic Fact Decomposition 2
Multi-Dimensional Frameworks for Language Model Evaluation 2
The Erosion of Safety Guardrails in Multi-Turn Dialogue 2
Overcoming the Limits of Multi Step Language Model Reasoning 2
Mitigating LLM Judge Bias Through Multi-Model Consensus 2
Why Language Models Prefer Their Own Writing 2
The Cross Architecture Validation Gap in Foundation Models 2
Evaluating the Faithfulness of Machine Learning Explanations 2
Scaling Specialized Language Model Interventions to Frontier Models 2
The Effective Context Window of Large Language Models 2

Top Authors

AuthorPapers
Sanmi Koyejo5
Kevin Zhu4
Adriano Koshiyama3
Ahmed M Ahmed3
Gjergji Kasneci3
Jan Batzner3
Ken Liu3
Matei Zaharia3
Philip Colin Treleaven3
Stefan Schmid3
Swabha Swayamdipta3
Volker Stocker3
Xia Hu3
Yu-Neng Chuang3
Zekun Wu3
Aman Chadha2
Arnav Goel2
Brando Miranda2
Dongqi Fu2
Elizabeth Anne Watkins2

Impactful Papers

Papers from this venue that shaped research clusters.

Foundational

Influential

Related Venues

Venues with the most similar research cluster distributions.

Papers

TitleYear
Scaling Laws for Upcycling Mixture-of-Experts Language Models2025
Search-Time Data Contamination2025
Silent Tokens, Loud Effects: Padding in LLMs2025
Small Changes, Large Consequences: Analyzing the Allocational Fairness of LLMs in Hiring Contexts2025
Smarter Sampling for LLM Judges: Reliable Evaluation on a Budget2025
SWE-InfraBench: Evaluating Language Models on Cloud Infrastructure Code2025
Sycophancy Claims about Language Models: The Missing Human-in-the-Loop2025
Talking with Oompa Loompas: A novel framework for evaluating linguistic acquisition of LLMs2025
T-FIX: Text-Based Explanations with Features Interpretable to eXperts2025
The Contamination Paradox: Why Test Set Leakage Can Be Both Potent and Negligible2025
The Impact of Post-training on Data Contamination2025
The Measure of All Measures: Quantifying LLM Benchmark Quality2025
The Narcissus Hypothesis: Descending to the Rung of Illusion2025
The Price of Progress: Algorithmic Efficiency and the Falling Cost of AI Inference2025
The Shepherd Test: How Will SuperIntelligent Agents Balance Care and Control in Asymmetric Relationships?2025
Towards Dynamic KV-Cache Compression: Fine-Grained Evaluation of Key and Value Ranks in LLMs2025
Towards Transparent Reasoning: What Drives Faithfulness in Large Language Models?2025
Train-before-Test Harmonizes Language Model Rankings2025
UQ: Assessing Language Models on Unsolved Questions2025
When Benchmarks Age: Temporal Misalignment through Large Language Model Factuality Evaluation2025
When LLM Meets Time Series: Can LLMs Perform Multistep Time Series Reasoning and Inference2025
Who Routes the Router: Rethinking the Evaluation of LLM Routing Systems2025
Whose Personae? Synthetic Persona Experiments in LLM Research and Pathways to Transparency2025
Why Do Multi-Agent LLM Systems Fail?2025

« prev Page 3/3