5 papers · 1 filter
Learning to Reason Across Parallel Samples for LLM Reasoning
Jianing Qi, Xi Ye, Hao Tang +2
Scaling test-time compute brings substantial performance gains for large language models (LLMs). By sampling multiple answers and heuristically aggregate their answers (e.g., eithe…
PropMEND: Hypernetworks for Knowledge Propagation in LLMs
Zeyu Leo Liu, Greg Durrett, Eunsol Choi
Knowledge editing techniques for large language models (LLMs) can inject knowledge that is later reproducible verbatim, but they fall short on propagating that knowledge: models ca…
From Distributional to Overton Pluralism: Investigating Large Language Model Alignment
Thom Lake, Eunsol Choi, Greg Durrett
The alignment process changes several properties of a large language model's (LLM's) output distribution. We analyze two aspects of post-alignment distributional shift of LLM respo…
CodeUpdateArena: Benchmarking Knowledge Editing on API Updates
Zeyu Leo Liu, Shrey Pandit, Xi Ye +2
Large language models (LLMs) are increasingly being used to synthesize and reason about source code. However, the static nature of these models' knowledge does not reflect the fact…
AmbigDocs: Reasoning across Documents on Different Entities under the Same Name
Yoonsang Lee, Xi Ye, Eunsol Choi
Different entities with the same name can be difficult to distinguish. Handling confusing entity mentions is a crucial skill for language models (LMs). For example, given the quest…