Related papers: Language Models are Homer Simpson! Safety Re-Align…
Large Language Models (LLMs) have achieved remarkable progress in reasoning, alignment, and task-specific performance. However, ensuring harmlessness in these systems remains a critical challenge, particularly in advanced models like…
Large reasoning models (LRMs) achieve strong performance on complex reasoning tasks but often generate harmful responses to malicious user queries. This paper investigates the underlying cause of these safety risks and shows that the issue…
Large language models (LLMs) are increasingly used as tool-augmented agents for multi-step decision making, yet training robust tool-using agents remains challenging. Existing methods still require manual intervention, depend on…
Safety alignment is crucial to ensure that large language models (LLMs) behave in ways that align with human preferences and prevent harmful actions during inference. However, recent studies show that the alignment can be easily compromised…
Traditional benchmarks for large language models (LLMs), such as HELM and AIR-BENCH, primarily assess safety through breadth-oriented evaluation across diverse tasks and risk categories. However, real-world deployment often exposes a…
The recent advancements of Large Language Models (LLMs) have spurred considerable research interest in extending their linguistic capabilities beyond text to other modalities, which leads to emergence of speech-based LLMs (SpeechLMs) with…
Safety alignment in large language models (LLMs) is achieved through fine-tuning mechanisms that regulate neuron activations to suppress harmful content. In this work, we propose a novel approach to induce disalignment by identifying and…
Text analysis of tabular data relies on two core operations: \emph{summarization} for corpus-level theme extraction and \emph{tagging} for row-level labeling. A critical limitation of employing large language models (LLMs) for these tasks…
Recent advancements in Large Language Models (LLMs) have sparked widespread concerns about their safety. Recent work demonstrates that safety alignment of LLMs can be easily removed by fine-tuning with a few adversarially chosen…
Fine-tuning Large Language Models (LLMs) has emerged as a common practice for tailoring models to individual needs and preferences. The choice of datasets for fine-tuning can be diverse, introducing safety concerns regarding the potential…
Large Language Models (LLMs) often generate overly cautious and vague responses on sensitive topics, sacrificing helpfulness for safety. Existing evaluation frameworks lack systematic methods to identify and address specific weaknesses in…
Despite progress in end-to-end ASR, real-world domain mismatches still cause performance drops, which Test-Time Adaptation (TTA) aims to mitigate by adjusting models during inference. Recent work explores combining TTA with external…
The widespread deployment of large language models (LLMs) across linguistic communities necessitates reliable multilingual safety alignment. However, recent efforts to extend alignment to other languages often require substantial resources,…
Memory safety violations in low-level code, written in languages like C, continues to remain one of the major sources of software vulnerabilities. One method of removing such violations by construction is to port C code to a safe C dialect.…
The emergence of finetuning-as-a-service has revealed a new vulnerability in large language models (LLMs). A mere handful of malicious data uploaded by users can subtly manipulate the finetuning process, resulting in an alignment-broken…
Fine-tuning large language models (LLMs) improves performance but introduces critical safety vulnerabilities: even minimal harmful data can severely compromise safety measures. We observe that perturbations orthogonal to the alignment…
Large language models (LLMs) demonstrate exceptional performance on complex reasoning tasks. However, despite their strong reasoning capabilities in high-resource languages (e.g., English and Chinese), a significant performance gap persists…
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…
Successful communication depends on the speaker's intended style (i.e., what the speaker is trying to convey) aligning with the listener's interpreted style (i.e., what the listener perceives). However, cultural differences often lead to…
Recent breakthroughs in Large Language Models (LLMs) have led to their adoption across a wide range of tasks, ranging from code generation to machine translation and sentiment analysis, etc. Red teaming/Safety alignment efforts show that…