7 papers
Large Language Models Should Learn Personalized Rather Than Aggregated Human Preferences
Cristina Garbacea
Current approaches to aligning large language models (LLMs) aggregate diverse human preferences into a single reward signal, effectively optimizing for a hypothetical ``average use…
Personalized Benchmarking: Evaluating LLMs by Individual Preferences
Cristina Garbacea, Heran Wang, Chenhao Tan
With the rise in capabilities of large language models (LLMs) and their deployment in real-world tasks, evaluating LLM alignment with human preferences has become an important chal…
HyPerAlign: Interpretable Personalized LLM Alignment via Hypothesis Generation
Cristina Garbacea, Chenhao Tan
Alignment algorithms are widely used to align large language models (LLMs) to human users based on preference annotations. Typically these (often divergent) preferences are aggrega…
RATE: Causal Explainability of Reward Models with Imperfect Counterfactuals
David Reber, Sean Richardson, Todd Nief +2
Reward models are widely used as proxies for human preferences when aligning or evaluating LLMs. However, reward models are black boxes, and it is often unclear what, exactly, they…
Evaluating the Goal-Directedness of Large Language Models
Tom Everitt, Cristina Garbacea, Alexis Bellot +4
To what extent do LLMs use their capabilities towards their given goal? We take this as a measure of their goal-directedness. We evaluate goal-directedness on tasks that require in…
Why is constrained neural language generation particularly challenging?
Cristina Garbacea, Qiaozhu Mei
Recent advances in deep neural language models combined with the capacity of large scale datasets have accelerated the development of natural language generation systems that produ…