6 accepted papers
While sparse autoencoders (SAEs) have generated significant excitement, a series of negative results have added to skepticism about their usefulness. Here, we establish a conceptual distinction that reconciles competing narratives surrounding SAEs. We argue that even if SAEs may be less effective fo…
Preference data is widely used for aligning language models, but remains largely opaque. While prior work has studied specific aspects of annotator preference (e.g., length or sycophancy), automatically inferring preferences without pre-specifying hypotheses remains challenging. We introduce *What's…
We describe HypotheSAEs, a general method to hypothesize interpretable relationships between text data (e.g., headlines) and a target variable (e.g., clicks). HypotheSAEs has three steps: (1) train a sparse autoencoder on text embeddings to produce interpretable features describing the data distribu…
Do LLMs align with human perceptions of safety? We study this question via *annotation alignment*, the extent to which LLMs and humans agree when annotating the safety of user-chatbot conversations. We leverage the recent DICES dataset (Aroyo et al. 2023), in which 350 conversations are each rated f…
Large language models (LLMs) are dramatically influencing AI research, spurring discussions on what has changed so far and how to shape the field’s future. To clarify such questions, we analyze a new dataset of 16,979 LLM-related arXiv papers, focusing on recent trends in 2023 vs. 2018-2022. First,…
Quantization, knowledge distillation, and magnitude pruning are among the most popular methods for neural network compression in NLP. Independently, these methods reduce model size and can accelerate inference, but their relative benefit and combinatorial interactions have not been rigorously studie…