5 papers
STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?
Hanxiang Chao, Yihan Bai, Rui Sheng +2
Large Language Model (LLM) agents are increasingly expected to maintain coherent, long-term personalized memory, yet current benchmarks primarily measure static fact retrieval, ove…
Search Arena: Analyzing Search-Augmented LLMs
Mihran Miroyan, Tsung-Han Wu, Logan King +8
Search-augmented language models combine web search with Large Language Models (LLMs) to improve response groundedness and freshness. However, analyzing these systems remains chall…
Prompt-to-Leaderboard
Evan Frick, Connor Chen, Joseph Tennyson +4
Large language model (LLM) evaluations typically rely on aggregated metrics like accuracy or human preference, averaging across users and prompts. This averaging obscures user- and…
How to Evaluate Reward Models for RLHF
Evan Frick, Tianle Li, Connor Chen +6
We introduce a new benchmark for reward models that quantifies their ability to produce strong language models through RLHF (Reinforcement Learning from Human Feedback). The gold-s…
From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline
Tianle Li, Wei-Lin Chiang, Evan Frick +5
The rapid evolution of Large Language Models (LLMs) has outpaced the development of model evaluation, highlighting the need for continuous curation of new, challenging benchmarks.…