Dependent Types, Proof Development, Ltac Programming, Mathematical Verification
In the Wild: Malware Prototype with Embedded Prompt Injection
research.checkpoint.com·18h
COIN: Uncertainty-Guarding Selective Question Answering for Foundation Models with Provable Risk Guarantees
arxiv.org·2h
Safe Pruning LoRA: Robust Distance-Guided Pruning for Safety Alignment in Adaptation of LLMs
arxiv.org·1d
Learning Instruction-Following Policies through Open-Ended Instruction Relabeling with Large Language Models
arxiv.org·2h
LOGICPO: Efficient Translation of NL-based Logical Problems to FOL using LLMs and Preference Optimization
arxiv.org·2d
Loading...Loading more...