Tag
This paper introduces GUARD-IT, a training-free method for machine unlearning that uses input-dependent activation steering at inference time to remove targeted knowledge from LLMs without modifying weights, matching or exceeding gradient-based baselines while preserving utility and robustness to quantization.
This article introduces SkillGen, a multi-agent framework that synthesizes and verifies reusable inference-time skills for LLM agents by contrasting successful and failed trajectories. The method ensures skills are auditable and empirically verified for their net positive impact on agent performance.
This paper introduces NoisyCoconut, an inference-time method that improves LLM reliability by injecting noise into latent trajectories to generate diverse reasoning paths. The approach enables models to abstain when uncertain, significantly reducing error rates in mathematical reasoning tasks without requiring retraining.
This paper introduces FLAS, a flow-based activation steering method that learns a concept-conditioned velocity field to steer language model activations at inference time. On the AxBench benchmark, FLAS is the first learned method to consistently outperform in-context prompting on held-out concepts without per-concept tuning.
PSRD framework halves multimodal hallucination in LVLMs by using phase-wise self-reward decoding and a distilled lightweight reward model without extra supervision.