conftrace_

safety risk

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

harmful content (2) ai safety (2) harmful behavior (1) large reasoning model (1) instruction-following retriever (1) malicious information retrieval (1) harmful passage (1) defense strategy (1) large language model (1) attack surface (1)

Papers

A Functionality-Grounded Benchmark for Evaluating Web Agents in E-commerce Domains ACL 2026 Exploiting Instruction-Following Retrievers for Malicious Information Retrieval ACL 2025 Safety in Large Reasoning Models: A Survey EMNLP 2025 Unintended Harms of Value-Aligned LLMs: Psychological and Empirical Insights ACL 2025