Related papers: Reasoning over Precedents Alongside Statutes: Case…
As large-scale language models increasingly impact safety-critical domains, ensuring their reliable adherence to well-defined principles remains a fundamental challenge. We introduce Deliberative Alignment, a new paradigm that directly…
Large Language Models (LLMs) have demonstrated remarkable success across various NLP benchmarks. However, excelling in complex tasks that require nuanced reasoning and precise decision-making demands more than raw language proficiency--LLMs…
Legal Artificial Intelligence (LegalAI) has achieved notable advances in automating judicial decision-making with the support of Large Language Models (LLMs). However, existing legal LLMs still struggle to generate reliable and…
While the wide adoption of refusal training in large language models (LLMs) has showcased improvements in model safety, recent works have highlighted shortcomings due to the shallow nature of these alignment methods. To this end, the work…
Recent studies on the safety alignment of large language models (LLMs) have revealed that existing approaches often operate superficially, leaving models vulnerable to various adversarial attacks. Despite their significance, these studies…
Recent advancements in large language models (LLMs) have accelerated progress toward artificial general intelligence, yet their potential to generate harmful content poses critical safety challenges. Existing alignment methods often…
Large Language Models (LLMs) are vulnerable to jailbreak attacks that exploit weaknesses in traditional safety alignment, which often relies on rigid refusal heuristics or representation engineering to block harmful outputs. While they are…
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…
Multimodal large-language models (MLLMs) often experience degraded safety alignment when harmful queries exploit cross-modal interactions. Models aligned on text alone show a higher rate of successful attacks when extended to two or more…
Large Language Models (LLMs) continue to exhibit vulnerabilities despite deliberate safety alignment efforts, posing significant risks to users and society. To safeguard against the risk of policy-violating content, system-level moderation…
Fine-tuning large language models (LLMs) based on human preferences, commonly achieved through reinforcement learning from human feedback (RLHF), has been effective in improving their performance. However, maintaining LLM safety throughout…
Optimizing large language models (LLMs) for downstream use cases often involves the customization of pre-trained LLMs through further fine-tuning. Meta's open release of Llama models and OpenAI's APIs for fine-tuning GPT-3.5 Turbo on custom…
With the rise of large language models (LLMs), ensuring they embody the principles of being helpful, honest, and harmless (3H), known as Human Alignment, becomes crucial. While existing alignment methods like RLHF, DPO, etc., effectively…
Safely aligning large language models (LLMs) often demands extensive human-labeled preference data, a process that's both costly and time-consuming. While synthetic data offers a promising alternative, current methods frequently rely on…
LLMs(Large Language Models) nowadays have widespread adoption as a tool for solving issues across various domain/tasks. These models since are susceptible to produce harmful or toxic results, inference-time adversarial attacks, therefore…
Large language models (LLMs) undergo safety alignment to ensure safe conversations with humans. However, this paper introduces a training-free attack method capable of reversing safety alignment, converting the outcomes of stronger…
Autonomous Driving (AD) encounters significant safety hurdles in long-tail unforeseen driving scenarios, largely stemming from the non-interpretability and poor generalization of the deep neural networks within the AD system, particularly…
Large Language Models (LLMs) demonstrate exceptional performance across diverse tasks by leveraging pre-trained (i.e., parametric) and external (i.e., contextual) knowledge. While substantial efforts have been made to enhance the…
Recent advancements in large language models (LLMs) have shifted the post-training paradigm from traditional instruction tuning and human preference alignment toward reinforcement learning (RL) focused on reasoning capabilities. However,…
Large Reasoning Models (LRMs) have achieved remarkable success on reasoning-intensive tasks such as mathematics and programming. However, their enhanced reasoning capabilities do not necessarily translate to improved safety performance-and…