6 papers
PolyAlign: Conditional Human-Distribution Alignment
L. D. M. S. Sai Teja, Ufaq Khan, Sathira Silva +2
Post-training methods such as supervised fine-tuning (SFT) and preference optimization typically align language models toward a single global assistant behavior. While effective fo…
CoLD: Counterfactually-Guided Length Debiasing for Process Reward Models in Mathematical Reasoning
Congmin Zheng, Jiachen Zhu, Jianghao Lin +6
Process Reward Models (PRMs) play a central role in evaluating and guiding multi-step reasoning in large language models (LLMs), especially for mathematical problem solving. Howeve…
Beyond Linear Steering: Unified Multi-Attribute Control for Language Models
Narmeen Oozeer, Luke Marks, Shreyans Jain +2
Controlling multiple behavioral attributes in large language models (LLMs) at inference time is a challenging problem due to interference between attributes and the limitations of…
Sleepless Nights, Sugary Days: Creating Synthetic Users with Health Conditions for Realistic Coaching Agent Interactions
Taedong Yun, Eric Yang, Mustafa Safdari +13
We present an end-to-end framework for generating synthetic users for evaluating interactive agents designed to encourage positive behavior changes, such as in health and lifestyle…
Out-of-Distribution Detection Methods Answer the Wrong Questions
Yucen Lily Li, Daohan Lu, Polina Kirichenko +4
To detect distribution shifts and improve model safety, many out-of-distribution (OOD) detection methods rely on the predictive uncertainty or features of supervised models trained…
Jailbreak Distillation: Renewable Safety Benchmarking
Jingyu Zhang, Ahmed Elgohary, Xiawei Wang +5
Large language models (LLMs) are rapidly deployed in critical applications, raising urgent needs for robust safety benchmarking. We propose Jailbreak Distillation (JBDistill), a no…