9 accepted papers
Standard bias benchmarks used for large language models (LLMs) measure the association between social attributes in model inputs and single-word model outputs. We test whether these benchmarks are robust to lengthening the model outputs via a more realistic user prompt, in the commonly studied domai…
Concept erasure techniques have recently gained significant attention for their potential to remove unwanted concepts from text-to-image models. While these methods often demonstrate promising results in controlled settings, their robustness in real-world applications and suitability for deployment…
Language model alignment is a critical step in training modern generative language models. Alignment targets to improve win rate of a sample from the aligned model against the base model. Today, we are increasingly using inference-time algorithms (e.g., Best-of-$N$ , controlled decoding, tree search…
A promising approach for improving reasoning in large language models is to use process reward models (PRMs). PRMs provide feedback at each step of a multi-step reasoning trace, improving credit assignment over outcome reward models (ORMs) that only provide feedback at the final step. However, colle…
We introduce a large language model (LLM) capable of processing speech inputs and show that tuning it further with reinforcement learning on human preference (RLHF) enables it to adapt better to disordered speech than traditional fine-tuning. Our method replaces low-frequency text tokens in an LLM’s…
A simple and effective method for the inference-time alignment of generative models is the best-of-$n$ policy, where $n$ samples are drawn from a reference policy, ranked based on a reward function, and the highest ranking one is selected. A commonly used analytical expression in the literature cla…
Disaggregated evaluation across subgroups is critical for assessing the fairness of machine learning models, but its uncritical use can mislead practitioners. We show that equal performance across subgroups is an unreliable measure of fairness when data are representative of the relevant populations…
A common approach for aligning language models to human preferences is to first learn a reward model from preference data, and then use this reward model to update the language model. We study two closely related problems that arise in this approach. First, any monotone transformation of the reward…
Machine learning models are often personalized based on information that is protected, sensitive, self-reported, or costly to acquire. These models use information about people, but do not facilitate nor inform their *consent*. Individuals cannot opt out of reporting information that a model needs t…