CORTEXA
← Browse
arxivcs.CLcs.AI2026-07-22

Sound Probabilistic Safety Bounds for Large Language Models

Mahdi Nazeri, Anne-Kathrin Schmuck, Sadegh Soudjani, Alessandro Abate

We propose a novel framework for computing rigorous bounds on the probability that a large language model (LLM) generates harmful output to a given prompt. We study a new application of the Clopper-Pearson confidence intervals to obtain probably approximately correct (PAC) bounds for this problem. As our main technical contribution, we propose an algorithm that leverages features in the latent space to prioritize exploring branches in the auto-regressive generation tree that are more likely to produce harmful outputs. Our approach in particular enables the efficient computation of useful lower bounds, even in scenarios where the true harm probability is extremely small, and crucially, the obtained lower bounds are sound, i.e., formally proven to be less than the actual harmfulness probability: our experimental results demonstrate the effectiveness of our method by computing non-trivial lower bounds on state-of-the-art LLMs. This study newly enables the evaluation and statistical certification of LLMs.

View free PDFSource page

Related papers

arxivcs.CLcs.AI2026-07-13

Comparing Semantic Navigation in Humans and Large Language Models using Natural Language Processing

Gabriel Paris-Colombo, Rodrigo M. Cabral-Carvalho, Felipe D. Toro-Hernández

Semantic memory retrieval can be conceptualized as navigation through conceptual space. We compared semantic search dynamics between humans and three large language models (GPT-4o, Gemini-2.5-Pro, Claude-Sonnet-4.5) using verbal fluency data. By applying trajectory-based NLP metr…

View free PDFSource page
arxivcs.AIcs.CLcs.LGcs.SIphysics.soc-ph2026-07-13

Reproducing human biases in route choice using large language models: Toward scalable behavioral modeling

Jiangtao Han, Shoufeng Ma, Shuxian Xu, Geng Li, Shuai Ling, Ning Jia, et al.

Human choice behavior, including route choice, exhibits systematic behavioral biases that deviate from the assumptions of full rationality. Cumulative prospect theory (CPT) has been widely recognized as an effective framework for characterizing such behavioral patterns. However,…

View free PDFSource page
arxivcs.CLcs.AI2026-07-19

Debate-on-Graph: Reliable and Adaptive Reasoning of Large Language Model on Uncertain Knowledge Graph

Peiji Yu, Xin Chen, Tianxing Wu

Large language models (LLMs) have demonstrated remarkable capabilities in natural language processing. However, LLMs often suffer from hallucinations and lack of relevant knowledge when dealing with question answering (QA) tasks. To mitigate these issues, knowledge graphs (KGs) h…

View free PDFSource page
arxivcs.AIcs.CLcs.HC2026-07-16

Benchmarking Multimodal Large Language Models for Scientific Visualization Literacy

Patrick Phuoc Do, Chau M. Ta, Chaoli Wang

Multimodal large language models (MLLMs) are increasingly used to interpret visualizations, yet current evaluations remain largely chart-centric and provide limited evidence of understanding of scientific visualization (SciVis). We benchmark six MLLMs on the scientific visualizat…

View free PDFSource page
arxivcs.AIcs.CL2026-07-11

SPARK: Susceptibility-Guided Profiling and Steering of Latent Reasoning States in Large Language Models

Dongxu Zhang, Yiding Sun, Zihao Guo, Xiangyang Yang, Kai Tang, Lin Chen, et al.

Reasoning failures in large language models (LLMs) are usually evaluated from final answers, but a wrong answer does not reveal why the model failed. The same incorrect output may reflect missing capability, an unstable reasoning trajectory, or a failure to activate a reasoning s…

View free PDFSource page