19 papers
Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks
Nobin Sarwar, Shubhashis Roy Dipta, Zheyuan Liu +1
With the growing adoption of VLMs, DMs, LLMs, and AFMs, these multimodal foundation models can inadvertently encode sensitive, copyrighted, biased, or unsafe cross-modal associatio…
Faithfulness as Information Flow: Evaluating and Training Faithful Chain-of-Thought Reasoning
Jinghan Jia, Joe Benton, Eric Easley
Chain-of-thought (CoT) reasoning is useful for monitoring language models only when the reasoning trace faithfully reflects the computation that produces the final answer. However,…
Downgrade to Upgrade: Optimizer Simplification Enhances Robustness in LLM Unlearning
Yicheng Lang, Yihua Zhang, Chongyu Fan +3
Large language model (LLM) unlearning aims to surgically remove the influence of undesired data or knowledge from an existing model while preserving its utility on unrelated tasks.…
CyclicReflex: Improving Reasoning Models via Cyclical Reflection Token Scheduling
Chongyu Fan, Yihua Zhang, Jinghan Jia +2
Large reasoning models (LRMs), such as OpenAI's o1 and DeepSeek-R1, harness test-time scaling to perform multi-step reasoning for complex problem-solving. This reasoning process, e…
Beyond SFT: Reinforcement Learning for Safer Large Reasoning Models with Better Reasoning Ability
Jinghan Jia, Nathalie Baracaldo, Sijia Liu
Large reasoning models (LRMs) extend large language models by generating explicit chain-of-thought (CoT) reasoning, significantly improving mathematical and logical problem solving…
BLUR: A Bi-Level Optimization Approach for LLM Unlearning
Hadi Reisizadeh, Jinghan Jia, Zhiqi Bu +6
Enabling large language models (LLMs) to unlearn knowledge and capabilities acquired during training has proven vital for ensuring compliance with data regulations and promoting et…