Showing cs.LGShow all
3 papers · 1 filter
cs.LG2025
Steering Language Model Refusal with Sparse Autoencoders
Kyle O'Brien, David Majercak, Xavier Fernandes +7
Responsible deployment of language models requires mechanisms for refusing unsafe prompts while preserving model performance. While most approaches modify model weights through add…
cs.LG2025
Inference-Time Scaling for Complex Tasks: Where We Stand and What Lies Ahead
Vidhisha Balachandran, Jingya Chen, Lingjiao Chen +8
Inference-time scaling can enhance the reasoning capabilities of large language models (LLMs) on complex problems that benefit from step-by-step problem solving. Although lengtheni…
cs.LG2024
Eureka: Evaluating and Understanding Large Foundation Models
Vidhisha Balachandran, Jingya Chen, Neel Joshi +6
Rigorous and reproducible evaluation is critical for assessing the state of the art and for guiding scientific advances in Artificial Intelligence. Evaluation is challenging in pra…