Related papers: TRACEALIGN -- Tracing the Drift: Attributing Align…

Large language models are increasingly relied upon as sources of information, but their propensity for generating false or misleading statements with high confidence poses risks for users and society. In this paper, we confront the critical…

Despite the fact that large language models (LLMs) show exceptional skill in instruction following tasks, this strength can turn into a vulnerability when the models are required to disregard certain instructions. Instruction-following…

The acquisition of agentic capabilities has transformed LLMs from "knowledge providers" to "action executors", a trend that while expanding LLMs' capability boundaries, significantly increases their susceptibility to malicious use. Previous…

Alignment is no longer a luxury, it is a necessity. As large language models (LLMs) enter high-stakes domains like education, healthcare, governance, and law, their behavior must reliably reflect human-aligned values and safety constraints.…

Recent studies show that Large Language Models (LLMs) with safety alignment can be jail-broken by fine-tuning on a dataset mixed with harmful data. First time in the literature, we show that the jail-broken effect can be mitigated by…

The current paradigm for safety alignment of large language models (LLMs) follows a one-size-fits-all approach: the model refuses to interact with any content deemed unsafe by the model provider. This approach lacks flexibility in the face…

We propose TraceRL, a trajectory-aware reinforcement learning framework for diffusion language models (DLMs) that incorporates preferred inference trajectory into post-training, and is applicable across different architectures. Equipped…

In an era of AI-generated misinformation flooding the web, existing tools struggle to empower users with nuanced, transparent assessments of content credibility. They often default to binary (true/false) classifications without contextual…

In Agentic AI, Large Language Models (LLMs) are increasingly used in the orchestration layer to coordinate multiple agents and to interact with external services, retrieval components, and shared memory. In this setting, failures are not…

Large reasoning models (LRMs) with multi-step reasoning capabilities have shown remarkable problem-solving abilities, yet they exhibit concerning safety vulnerabilities that remain poorly understood. In this work, we investigate why safety…

A common solution for mitigating outdated or incorrect information in Large Language Models (LLMs) is to provide updated facts in-context or through knowledge editing. However, these methods introduce knowledge conflicts when the knowledge…

Instruction Fine-Tuning (IFT) has been widely adopted as an effective post-training strategy to enhance various abilities of Large Language Models (LLMs). However, prior studies have shown that IFT can significantly compromise LLMs' safety,…

Large Language Models (LLMs) demonstrate impressive capabilities across various fields, yet their increasing use raises critical security concerns. This article reviews recent literature addressing key issues in LLM security, with a focus…

Recently, Large Language Models (LLMs) have made significant advancements and are now widely used across various domains. Unfortunately, there has been a rising concern that LLMs can be misused to generate harmful or malicious content.…

Instruction following refers to the ability of large language models (LLMs) to generate outputs that satisfy all specified constraints. Existing research has primarily focused on constraint categories, offering limited evaluation dimensions…

Alignment faking (AF) occurs when an LLM strategically complies with training objectives to avoid value modification, reverting to prior preferences once monitoring is lifted. Current detection methods focus on conversational settings and…

Large-scale cross-lingual pre-trained language models (xPLMs) have shown effectiveness in cross-lingual sequence labeling tasks (xSL), such as cross-lingual machine reading comprehension (xMRC) by transferring knowledge from a high-resource…

Large language models are increasingly embedded into systems that interact with user data, retrieved web content, and external tools, creating a new attack surface: prompt injection, where malicious commands embedded in untrusted data…

Large language models demonstrate reasonable multilingual abilities, despite predominantly English-centric pretraining. However, the spontaneous multilingual alignment in these models is shown to be weak, leading to unsatisfactory…

Safety alignment aims to ensure that large language models (LLMs) refuse harmful requests by post-training on harmful queries paired with refusal answers. Although safety alignment is widely adopted in industry, the overrefusal problem…