Divergence Decoding (DD) is a novel, effective, and inexpensive method that uses auxiliary models to steer LLM logits during inference, enabling the removal of memorized sensitive data without signifi…

DenoiseRL is a novel reinforcement learning framework that improves reasoning in large language models by optimizing directly from the failures and incorrect reasoning traces of weak models, eliminati…

The paper proposes a comprehensive framework for LLM-based agent unlearning, enabling agents to selectively forget specific knowledge (states, trajectories, or environments) while maintaining performa…

The paper proposes a novel, theoretically-grounded algorithm (HAMU) that addresses the challenge of machine unlearning by guaranteeing specified improvements in forget quality while minimizing retain…

This paper introduces Anchored Weight Decay (AWD), a regularization technique that effectively prevents prior-task forgetting during LLM fine-tuning with Evolution Strategies (ES), positioning ES as a…

The paper introduces AMNESIA, the first large-scale, open-source benchmark for medical unlearning, demonstrating that current unlearning methods struggle to separate individual patient data from share…

The paper proposes a novel bi-level exact unlearning attack targeting Large Reasoning Models (LRMs) that forces incorrect final answers while generating misleading reasoning traces, highlighting new s…

The paper introduces a novel, non-deep neural network architecture that achieves the performance of LLMs by finding the global optimum of the loss function in a single, closed-form iteration, eliminat…

The paper proposes Guided Denoiser Self-Distillation (GDSD), a novel method that bypasses the use of likelihood surrogates (like ELBO) in RL for diffusion language models, achieving state-of-the-art p…

The paper proposes $D^3$, a dynamic graph-constrained scheduling framework that optimizes LLM training order by modeling sample interactions as a dynamic influence graph.

The paper introduces SAVE, a framework that uses on-policy feedback and the value function to self-supervise and improve reward models, significantly enhancing RLHF performance across multiple benchma…

This paper proposes four guidelines and two novel data ordering methods (STR and SAW) to systematically optimize data organization, significantly enhancing the stability and performance of LLM trainin…

The paper introduces 5WBENCH, a new benchmark for causal unlearning, and proposes MAAT, a novel three-phase framework that achieves high forgetting and high retention specifically on complex 'Why'-typ…

ExpWeaver introduces a novel framework for LLM agents to learn from past experiences using latent retrieval-augmented generation, achieving state-of-the-art performance while significantly improving t…

PURGE is a novel machine unlearning algorithm that leverages the duality between continual learning and unlearning to achieve high data retention while making the unlearned model indistinguishable fro…

This paper provides the first integrated analysis of model dememorization, unifying unlearnability and unlearning methods, and offering theoretical guarantees on dememorization depth.

The paper introduces Synthesis Data Reversion (SDR), a method that infers the data laundering transformation used in LLM training and synthesizes queries to restore the detection signals lost when pro…

This paper proposes a new framework called STRIDE for training data attribution in Large Language Models.

Weak self-training on synthetic data can amplify a language model's existing capabilities, but this effect is strictly dependent on the compatibility between the source and student models, not on the…