Related papers: BioRefusalAudit: Auditing Biosecurity Refusal Dept…
Safety alignment approaches in large language models (LLMs) often lead to the over-refusal of benign queries, significantly diminishing their utility in sensitive scenarios. To address this challenge, we introduce FalseReject, a…
We probe OpenAI's open-weights 20-billion-parameter model gpt-oss-20b to study how sociopragmatic framing, language choice, and instruction hierarchy affect refusal behavior. Across 80 seeded iterations per scenario, we test several harm…
Since the release of OpenAI's ChatGPT, generative language models have attracted extensive public attention. The increased usage has highlighted generative models' broad utility, but also revealed several forms of embedded bias. Some is…
As vision-language models (VLMs) become increasingly capable, maintaining a balance between safety and usefulness remains a central challenge. Safety mechanisms, while essential, can backfire, causing over-refusal, where models decline…
Safety-aligned large language models (LLMs) sometimes falsely refuse pseudo-harmful prompts, like "how to kill a mosquito," which are actually harmless. Frequent false refusals not only frustrate users but also provoke a public backlash…
Safety alignment in large language models (LLMs) induces over-refusals -- where LLMs decline benign requests due to aggressive safety filters. We analyze this phenomenon in retrieval-augmented generation (RAG), where both the query intent…
Conversational large language models are fine-tuned for both instruction-following and safety, resulting in models that obey benign requests but refuse harmful ones. While this refusal behavior is widespread across chat models, its…
Safety alignment in Large Language Models is critical for healthcare; however, reliance on binary refusal boundaries often results in \emph{over-refusal} of benign queries or \emph{unsafe compliance} with harmful ones. While existing…
Large Language Models (LLMs) are widely used across sectors, yet their alignment with International Humanitarian Law (IHL) is not well understood. This study evaluates eight leading LLMs on their ability to refuse prompts that explicitly…
Safety evaluations of large language models (LLMs) typically report binary outcomes, i.e. attack success rate (ASR), refusal rate, or harmful versus safe classification, which hide how risk changes between prompt and response. We present a…
Safety architectures for language models increasingly rely on external monitors to detect errors and inject corrective signals at inference time. For such systems to function in interactive settings, models must be able to incorporate…
In this paper, we investigate whether refusal behavior can be predicted from LLM intermediate activations before decoding using linear probes trained on residual stream activations at each transformer block. We find that refusal is linearly…
Large Language Models (LLMs) reproduce social biases, yet prevailing evaluations score models in isolation, obscuring how biases persist across families and releases. We introduce Bias Similarity Measurement (BSM), which treats fairness as…
Recent advancements in large language models (LLMs) have demonstrated that fine-tuning and human alignment can render LLMs harmless. In practice, such "harmlessness" behavior is mainly achieved by training models to reject harmful requests,…
Safety-aligned language models often refuse cybersecurity requests whose wording resembles misuse, even when the task is authorized and defensive. This makes security evaluation ambiguous: a failed answer may reflect missing capability or…
Large Language Models used in ChatGPT have traditionally been trained to learn a refusal boundary: depending on the user's intent, the model is taught to either fully comply or outright refuse. While this is a strong mitigation for…
Safety-trained language models routinely refuse requests for help circumventing rules. But not all rules deserve compliance. When users ask for help evading rules imposed by an illegitimate authority, rules that are deeply unjust or absurd…
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…
Large language models (LLMs) trained on internet-scale corpora can exhibit systematic biases that increase the probability of unwanted behavior. In this study, we examined potential biases towards synthetic vs. biological technological…
Large language models and LLM-based agents are increasingly used for cybersecurity tasks that are inherently dual-use. Existing approaches to refusal, spanning academic policy frameworks and commercially deployed systems, often rely on…