2 citations · 8 across the 46 of their papers we have counts for
5 papers · 1 filter
Self-Consistency Falls Short! The Adverse Effects of Positional Bias on Long-Context Problems
Adam Byerly, Daniel Khashabi
Self-consistency (SC) improves the performance of large language models (LLMs) across various tasks and domains that involve short content. However, does this support its effective…
Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements
Jingyu Zhang, Ahmed Elgohary, Ahmed Magooda +2
The current paradigm for safety alignment of large language models (LLMs) follows a one-size-fits-all approach: the model refuses to interact with any content deemed unsafe by the…
Upsample or Upweight? Balanced Training on Heavily Imbalanced Datasets
Tianjian Li, Haoran Xu, Weiting Tan +2
Data abundance across different domains exhibits a long-tailed distribution: few domains have abundant data, while most face data scarcity. Our work focuses on a multilingual setti…
RATIONALYST: Mining Implicit Rationales for Process Supervision of Reasoning
Dongwei Jiang, Guoxuan Wang, Yining Lu +5
The reasoning steps generated by LLMs might be incomplete, as they mimic logical leaps common in everyday communication found in their pre-training data: underlying rationales are…
SELF-[IN]CORRECT: LLMs Struggle with Discriminating Self-Generated Responses
Dongwei Jiang, Jingyu Zhang, Orion Weller +3
Can LLMs consistently improve their previous outputs for better results? For this to be true, LLMs would need to be better at discriminating among previously-generated alternatives…