Related papers: Classifier-free guidance in LLMs Safety
As concerns around data privacy in machine learning grow, the ability to unlearn, or remove, specific data points from trained models becomes increasingly important. While state of the art unlearning methods have emerged in response, they…
Multi-label classification (MLC) assigns multiple labels to each sample. Prior studies show that MLC can be transformed to a sequence prediction problem with a recurrent neural network (RNN) decoder to model the label dependency. However,…
VLMs trained on web-scale data retain sensitive and copyrighted visual concepts that deployment may require removing. Training-based unlearning methods share a structural flaw: fine-tuning on a narrow forget set degrades general…
Designing missiles' autopilot controllers has been a complex task, given the extensive flight envelope and the nonlinear flight dynamics. A solution that can excel both in nominal performance and in robustness to uncertainties is still to…
Machine unlearning for large language models (LLMs) aims to remove targeted knowledge while preserving general capability. In this paper, we recast LLM unlearning as an asymmetric two-task problem: retention is the primary objective and…
During pretraining, LLMs inadvertently memorize sensitive or copyrighted data, posing significant compliance challenges under legal frameworks like the GDPR and the EU AI Act. Fulfilling these mandates demands techniques that can remove…
Aligning large language models (LLMs) with human preferences usually requires fine-tuning methods such as RLHF and DPO. These methods directly optimize the model parameters, so they cannot be used in test-time to improve model performance,…
Large Reasoning Models (LRMs) excel in structured tasks by emulating deliberate human reasoning but often suffer from overthinking, degrading performance and wasting resources. One possible baseline is to deploy both LLM and LRM, then route…
Large Language Models (LLMs) are versatile and demonstrate impressive generalization ability by mining and learning information from extensive unlabeled text. However, they still exhibit reasoning mistakes, often stemming from knowledge…
Training large language models (LLMs) is a costly endeavour in terms of time and computational resources. The large amount of training data used during the unsupervised pre-training phase makes it difficult to verify all data and,…
The growing disparity between the exponential scaling of computational resources and the finite growth of high-quality text data now constrains conventional scaling approaches for large language models (LLMs). To address this challenge, we…
The main focus of this paper is on enhancement of two types of game-theoretic learning algorithms: log-linear learning and reinforcement learning. The standard analysis of log-linear learning needs a highly structured environment, i.e.…
As Large Language Models (LLMs) receive increasing attention and are being deployed across various domains, their potential risks, including generating harmful or biased content, producing unsupported claims, and exhibiting vulnerabilities…
Machine unlearning, a process enabling pre-trained models to remove the influence of specific training samples, has attracted significant attention in recent years. While extensive research has focused on developing efficient unlearning…
Reinforcement Learning (RL) has emerged as an efficient method of choice for solving complex sequential decision making problems in automatic control, computer science, economics, and biology. In this paper we present a model-free RL…
Large language models (LLMs) trained on unfiltered corpora inherently risk retaining sensitive information, necessitating selective knowledge unlearning for regulatory compliance and ethical safety. However, existing parameter-modifying…
Large Language Models are typically trained on datasets collected from the web, which may inadvertently contain harmful or sensitive personal information. To address growing privacy concerns, unlearning methods have been proposed to remove…
Recent advances in reinforcement learning (RL) enable its use on increasingly complex tasks, but the lack of formal safety guarantees still limits its application in safety-critical settings. A common practical approach is to augment the RL…
While reinforcement learning (RL) holds great potential for decision making in the real world, it suffers from a number of unique difficulties which often need specific consideration. In particular: it is highly non-stationary; suffers from…
Reinforcement Learning with Verifiable Rewards (RLVR) has become a promising paradigm for scaling reasoning capabilities of Large Language Models (LLMs). However, the sparsity of binary verifier rewards often leads to low efficiency and…