3 accepted papers
In correctness-sensitive scenarios, it is crucial for Large Language Models (LLMs) to strictly follow the provided evidence. However, even with reference texts, models often suffer from hallucinations, especially when processing long contexts. Existing work attempts to reinforce the use of citations…
Formal verification provides strong guarantees of software correctness, but its adoption is limited by the high cost of writing precise formal specifications. While recent large language models (LLMs) have demonstrated impressive capabilities in theorem proving and verified code generation, how powe…
Tool-calling text-to-image (T2I) agents can plan and execute multi-step tool chains to accomplish complex generation and editing queries. However, this capability introduces a new safety attack surface: harmful outputs may arise from tool orchestration, where individually benign steps combine into u…