11 accepted papers
Language models are increasingly capable and are being rapidly deployed on a population-level scale. As a result, the safety of these models is increasingly high-stakes. Fortunately, advances in alignment have significantly reduced the likelihood of harmful model outputs. However, when models are qu…
Reward hacking, where a reasoning model exploits loopholes in a reward function to achieve high rewards without solving the intended task, poses a significant threat. This behavior may be explicit, i.e. verbalized in the model's chain-of-thought (CoT), or implicit, where the CoT appears benign thus…
Jailbreak transferability is the surprising phenomenon when an adversarial attack compromising one model also elicits harmful responses from other models. Despite widespread demonstrations, there is little consensus on why transfer is possible: is it a quirk of safety training, an artifact of model…
As LLMs become more agentic, a critical risk emerges: attackers can \emph{decompose} harmful goals into stateful, benign subtasks that trick LLM agents into executing them without realizing the harmful intent in the same context. The challenge lies in the existing shallow safety alignment techniques…
While semidefinite programming (SDP) has traditionally been limited to moderate-sized problems, recent algorithms augmented with matrix sketching techniques have enabled solving larger SDPs. However, these methods achieve scalability at the cost of an increase in the number of necessary iterations,…
What latent features are encoded in language model (LM) representations? Recent work on training sparse autoencoders (SAEs) to disentangle interpretable features in LM representations has shown significant promise. However, evaluating the quality of these SAEs is difficult because we lack a ground-t…
Efficient k-nearest neighbor search is a fundamental task, foundational for many problems in NLP. When the similarity is measured by dot-product between dual-encoder vectors or L2-distance, there already exist many scalable and efficient search methods. But not so when similarity is measured by more…
Learning representations of entity mentions is a core component of modern entity linking systems for both candidate generation and making linking predictions. In this paper, we present and empirically analyze a novel training approach for learning mention and entity representations that is based on…
We consider the problem of clustering with user feedback. Existing methods express constraints about the input data points, most commonly through must-link and cannot-link constraints on data point pairs. In this paper, we introduce existential cluster constraints: a new form of feedback where users…
Due to large number of entities in biomedical knowledge bases, only a small fraction of entities have corresponding labelled training data. This necessitates entity linking models which are able to link mentions of unseen entities using learned representations of entities. Previous approaches link e…
Archived data from the US network of weather radars hold detailed information about bird migration over the last 25 years, including very high-resolution partial measurements of velocity. Historically, most of this spatial resolution is discarded and velocities are summarized at a very small number…