Selected Publications

Protein representation learning has advanced rapidly with the scale-up of sequence and structure supervision, but most models still encode proteins either as per-residue token sequences or as single global embeddings. This overlooks a defining property of protein organization: proteins are built from recurrent, evolutionarily conserved substructures that concentrate biochemical activity and mediate core molecular functions. Although substructures such as domains and functional sites are systematically cataloged, they are rarely used as training signals or representation units in protein models. We introduce Magneton, an environment for developing substructure-aware protein models. Magneton provides (1) a dataset of 530,601 proteins annotated with over 1.7 million substructures spanning 13,075 types, (2) a training framework for incorporating substructures into existing protein models, and (3) a benchmark suite of 13 tasks probing representations at the residue, substructural, and protein levels. Using Magneton, we develop substructure-tuning, a supervised fine-tuning method that distills substructural knowledge into pretrained protein models. Across state-of-the-art sequence- and structure-based models, substructure-tuning improves function prediction, yields more consistent representations of substructure types never observed during tuning, and shows that substructural supervision provides information that is complementary to global structure inputs. The Magneton environment, datasets, and substructure-tuned models are all openly available at https://github.com/rcalef/magneton.

Real-world tasks and environments exhibit differences from the static datasets that large language models (LLMs) are typically evaluated on. Such tasks can involve sequential interaction, requiring coherent updating of beliefs in light of new evidence, and making appropriate decisions based on those beliefs. Predicting how LLMs will perform in such dynamic environments is important, but can be tricky to determine from measurements in static settings. In this work, we examine two critical components of LLM performance: the ability of LLMs to coherently update their beliefs, and the extent to which the actions they take are consistent with those beliefs. First, we find that LLMs are largely inconsistent in how they update their beliefs; models can exhibit up to a 30% average difference between the directly elicited posterior, and the correct update of their prior. Second, we find that LLMs also often take actions which are inconsistent with the beliefs they hold. On a betting market, for example, LLMs often do not even bet in the same direction as their internally held beliefs over the underlying outcomes. We also find they have moderate self-inconsistency in how they respond to challenges by users to given answers. Finally, we show that the above properties hold even for strong models that obtain high accuracy or that are well-calibrated on the tasks at hand. Our results highlight the difficulties of predicting LLM behavior in complex real-world settings.