254 citations · 662 across the 53 of their papers we have counts for
6 papers · 2 filters
Evaluating Context Compaction on the Questions That Come Later
Junwei Yao, Yongxi Zhou, Zike Yang +4
Language-model agents compact their context for the question at hand, but the compacted context must also serve questions that come later. We evaluate compaction on these later que…
Forty Shades of Blue: Quality-Diversity Alignment via Mode-Conditioned Reinforcement Learning
Jiayi Yuan, Hangoo Kang, James Jihao Liu +4
A notable byproduct of LLM alignment training is mode collapse: the progressive loss of output diversity that narrows a model's expressivity at inference time. This degradation is…
SPADE: Self-Play in Adaptive Synthetic Executable Environments
Bo Liu, Simon Yu, Yiding Jiang +15
Continuous self-improvement requires an ever-expanding pool of self-generated, diverse, adaptive goals. For language agents, existing training environment pools (hand-curated, stat…
Pigeonholing: how bad prompts hurt models, causing collapse and mistakes
Hyunji Nam, Keertana Chidambaram, Dorottya Demszky +1
While in-context learning is generally shown to be effective in Large Language Models (LLMs), bad contexts can cause performance degradation and mode collapse, a phenomenon we call…
How LLMs Distort Our Written Language
Marwa Abdulhai, Isadora White, Yanming Wan +4
Large language models (LLMs) are used by over a billion people globally, most often to assist with writing. In this work, we demonstrate that LLMs not only alter the voice and tone…
Are Language Models Sensitive to Morally Irrelevant Distractors?
Andrew Shaw, Christina Hahn, Catherine Rasgaitis +5
With the rapid uptake of large language models (LLMs) across high-stakes settings, it is becoming increasingly important to ensure that LLMs behave in ways that align with human va…