Related papers: Understanding Refusal in Language Models with Spar…
Large Vision-Language Models (LVLMs) have shown remarkable capabilities across a wide range of multimodal tasks. However, their integration of visual inputs introduces expanded attack surfaces, thereby exposing them to novel security…
Large language models (LLMs) have transformed the way we access information. These models are often tuned to refuse to comply with requests that are considered harmful and to produce responses that better align with the preferences of those…
Large language models (LLMs), despite being safety-aligned, exhibit brittle refusal behaviors that can be circumvented by simple linguistic changes. As tense jailbreaking demonstrates that models refusing harmful requests often comply when…
Safety-aligned language models refuse harmful requests through learned refusal behaviors encoded in their internal representations. Recent activation-based jailbreaking methods circumvent these safety mechanisms by applying orthogonal…
Large language models (LLMs) are widely deployed as general-purpose tools, yet extended interaction can reveal behavioral patterns not captured by standard quantitative benchmarks. We present a qualitative case-study methodology for…
Large language models can resist task-misaligned activation steering during inference, sometimes recovering mid-generation to produce improved responses even when steering remains active. We term this Endogenous Steering Resistance (ESR).…
Large language models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks, yet they often refuse to answer legitimate queries--a phenomenon known as overrefusal. Overrefusal typically stems from over-conservative…
Safety-aligned language models often refuse prompts that are actually harmless. Current evaluations mostly report global rates such as false rejection or compliance. These scores treat each prompt alone and miss local inconsistency, where a…
Large Language Models (LLMs) have achieved strong complex reasoning capabilities through Chain-of-Thought (CoT) reasoning. However, their reasoning patterns remain too complicated to analyze. While Sparse Autoencoders (SAEs) have emerged as…
Frontier large language models are increasingly deployed as orchestration backbones for biological research workflows, yet no shared evidence base exists for comparing their refusal behaviour on legitimate research prompts. RefusalBench,…
Current LLMs are trained to refuse potentially harmful input queries regardless of whether users actually had harmful intents, causing a tradeoff between safety and user experience. Through a study of 480 participants evaluating 3,840…
Existing large language models (LLMs) occasionally generate plausible yet factually incorrect responses, known as hallucinations. Two main approaches have been proposed to mitigate hallucinations: retrieval-augmented language models (RALMs)…
Sparse autoencoders (SAEs) are a popular tool for interpreting large language model activations, but their utility in addressing open questions in interpretability remains unclear. In this work, we demonstrate their effectiveness by using…
This study addresses a critical gap in safety tuning practices for Large Language Models (LLMs) by identifying and tackling a refusal position bias within safety tuning data, which compromises the models' ability to appropriately refuse…
Large language models (LLMs) frequently produce false refusals, declining benign requests that contain terms resembling unsafe queries. We address this challenge by introducing two comprehensive benchmarks: the Exaggerated Safety Benchmark…
Large language models (LLMs) demonstrate exceptional performance on tasks requiring complex linguistic abilities, such as reference disambiguation and metaphor recognition/generation. Although LLMs possess impressive capabilities, their…
Large language models (LLMs) have significantly advanced dialogue systems and role-playing agents through their ability to generate human-like text. While prior studies have shown that LLMs can exhibit distinct and consistent personalities,…
The proliferation of large language models (LLMs) has sparked widespread and general interest due to their strong language generation capabilities, offering great potential for both industry and research. While previous research delved into…
Large Language Models (LLMs) have revolutionized artificial intelligence, demonstrating remarkable computational power and linguistic capabilities. However, these models are inherently prone to various biases stemming from their training…
Abstention, the refusal of large language models (LLMs) to provide an answer, is increasingly recognized for its potential to mitigate hallucinations and enhance safety in LLM systems. In this survey, we introduce a framework to examine…