5 papers
Mitigating Misalignment Contagion by Steering with Implicit Traits
Maria Chang, Ronny Luss, Miao Liu +3
Language models (LMs) are increasingly used in high-stakes, multi-agent settings, where following instructions and maintaining value alignment are critical. Most alignment research…
Cross-Examiner: Evaluating Consistency of Large Language Model-Generated Explanations
Danielle Villa, Maria Chang, Keerthiram Murugesan +2
Large Language Models (LLMs) are often asked to explain their outputs to enhance accuracy and transparency. However, evidence suggests that these explanations can misrepresent the…
Final-Model-Only Data Attribution with a Unifying View of Gradient-Based Methods
Dennis Wei, Inkit Padhi, Soumya Ghosh +3
Training data attribution (TDA) is concerned with understanding model behavior in terms of the training data. This paper draws attention to the common setting where one has access…
Reasoning about concepts with LLMs: Inconsistencies abound
Rosario Uceda-Sosa, Karthikeyan Natesan Ramamurthy, Maria Chang +1
The ability to summarize and organize knowledge into abstract concepts is key to learning and reasoning. Many industrial applications rely on the consistent and systematic use of c…
Alignment Studio: Aligning Large Language Models to Particular Contextual Regulations
Swapnaja Achintalwar, Ioana Baldini, Djallel Bouneffouf +16
The alignment of large language models is usually done by model providers to add or control behaviors that are common or universally understood across use cases and contexts. In co…