相关论文: Surgical, Cheap, and Flexible: Mitigating False Re…

We consider the challenge of mitigating the generation of negative or toxic content by the Large Language Models (LLMs) in response to certain prompts. We propose integrating risk-averse principles into LLM fine-tuning to minimize the…

Large Language Models (LLMs) often produce hallucinated or unverifiable content, undermining their reliability in factual domains. This work investigates Reinforcement Learning with Verifiable Rewards (RLVR) as a training paradigm that…

We present Gabliteration, a novel neural weight modification technique that advances beyond traditional abliteration methods by implementing adaptive multi-directional projections with regularized layer selection. Our approach addresses the…

Multimodal Large Language Models (MLLMs) frequently suffer from hallucination issues, generating information about objects that are not present in input images during vision-language tasks. These hallucinations particularly undermine model…

Large language models are increasingly used to answer and verify scientific claims, yet existing evaluations typically assume that a model must always produce a definitive answer. In scientific settings, however, unsupported or uncertain…

With the growing adoption of Large Language Models (LLMs) in critical areas, ensuring their security against jailbreaking attacks is paramount. While traditional defenses primarily rely on refusing malicious prompts, recent logit-level…

We tackle the problem of computing counterfactual explanations -- minimal changes to the features that flip an undesirable model prediction. We propose a solution to this question for linear Support Vector Machine (SVMs) models. Moreover,…

Large vision-language models (LVLMs) often hallucinate content that is fluent yet unsupported by the image, limiting their reliability in real-world deployment. We show that a key failure mode arises from route competition: even when visual…

Large language models (LLMs) aligned for safety often suffer from over-refusal, the tendency to reject seemingly toxic or benign prompts by misclassifying them as toxic. This behavior undermines models' helpfulness and restricts usability…

Recently, substantial progress has been made in language modeling by using deep neural networks. However, in practice, large scale neural language models have been shown to be prone to overfitting. In this paper, we present a simple yet…

Large language models (LLMs), despite possessing latent safety understanding from their vast pretraining data, remain vulnerable to generating harmful content and exhibit issues such as over-refusal and utility degradation after safety…

Recent studies on AI security have highlighted the vulnerability of Vision-Language Pre-training (VLP) models to subtle yet intentionally designed perturbations in images and texts. Investigating multimodal systems' robustness via…

Recently, the development of open-source large language models (LLMs) has advanced rapidly. Nevertheless, due to data constraints, the capabilities of most open-source LLMs are primarily focused on English. To address this issue, we…

Language models (LMs) are increasingly used to build agents that can act autonomously to achieve goals. During this automatic process, agents need to take a series of actions, some of which might lead to severe consequences if incorrect…

Learning with rejection is an important framework that can refrain from making predictions to avoid critical mispredictions by balancing between prediction and rejection. Previous studies on cost-based rejection only focused on the…

Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in processing and reasoning over diverse modalities, but their advanced abilities also raise significant privacy concerns, particularly regarding Personally…

The deployment of pre-trained perception models in novel environments often leads to performance degradation due to distributional shifts. Although recent artificial intelligence approaches for metacognition use logical rules to…

Reliability of LLMs is questionable even as they get better at more tasks. A wider adoption of LLMs is contingent on whether they are usably factual. And if they are not, on whether they can properly calibrate their confidence in their…

We develop a new approach to multi-label conformal prediction in which we aim to output a precise set of promising prediction candidates with a bounded number of incorrect answers. Standard conformal prediction provides the ability to adapt…

Large language models have been shown to memorize significant portions of their training data, which they can reproduce when appropriately prompted. This work investigates the impact of simple pruning techniques on this behavior. Our…