6 papers · 1 filter
Faithful Latent Harm Monitors Work No Better Than the Models Own Behaviour at a Matched False Alarm Rate
Abhishek Mishra, Sagnik Chatterjee, Suyash Maniyar
Large language models have been reported to encode the harmfulness of a request separately from their decision to refuse it, and latent safety monitors such as Latent Guard build o…
SCOPE: Siamese Contrastive Operon Pair Embeddings for Functional Sequence Representation and Classification
Akarsh Gupta, Kenneth Rodrigues, Sagnik Chatterjee
Identifying operons is a fundamental step in understanding prokaryotic gene regulation, as classifying genes into operons supports the reconstruction of regulatory networks, functi…
Trajectory Supervision for Continual Tool-Use Learning in LLMs
Vishnu Vardhan Reddy, Sagnik Chatterjee, Soumik Bhatta
Most language-model training data shows final artifacts, not the process that produced them. We study a tractable version of this question in tool use: when a model learns a stream…
Convex Basins in Single-Index Model Loss Landscapes: Applications to Robust Recovery under Strong Adversarial Corruption
Santanu Das, Sagnik Chatterjee, Jatin Batra
We study the problem of robustly learning Gaussian Single Index Models (SIMs) in the presence of heavy-tailed noise and a constant fraction of adversarially corrupted covariates an…
Dual-Track CoT: Budget-Aware Stepwise Guidance for Small LMs
Sagnik Chatterjee, Atharva Patil, Sricharan Ramesh
Large Language Models (LLMs) solve many reasoning tasks via chain-of-thought (CoT) prompting, but smaller models (about 7 to 8B parameters) still struggle with multi-step reasoning…
Perfect Secret Key Generation for a class of Hypergraphical Sources
Manuj Mukherjee, Sagnik Chatterjee, Alhad Sethi
Nitinawarat and Narayan proposed a perfect secret key generation scheme for the so-called \emph{pairwise independent network (PIN) model} by exploiting the combinatorial properties…