PQR: A Framework to Generate Diverse and Realistic User Queries that Elicit QA Agent Failures
cs.CL
Submitted: 2026-05-15
Updated: 2026-10-09
Sources
- GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
- Graph of Attacks: Improved Black-Box and Interpretable Jailbreaks for LLMs
- Constitutional AI: Harmlessness from AI Feedback
- Jailbreaking Black Box Large Language Models in Twenty Queries
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- CRMArena-Pro: Holistic Assessment of LLM Agents Across Diverse Business Scenarios and Interactions
- SECA: Semantically Equivalent and Coherent Attacks for Eliciting LLM Hallucinations
- AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models
- Tree of Attacks: Jailbreaking Black-Box LLMs Automatically
- SAGE: A Top-Down Bottom-Up Knowledge-Grounded User Simulator for Multi-turn AGent Evaluation
- Auto-Prompt Generation is Not Robust: Prompt Optimization Driven by Pseudo Gradient
- Gemma 3 Technical Report
- Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models
- Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations
- An LLM can Fool Itself: A Prompt-Based Adversarial Attack
- Qwen3 Technical Report
- $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
- Jailbreak Attacks and Defenses Against Large Language Models: A Survey
- GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering