RT-LRM benchmark finds Large Reasoning Models more fragile than standard LLMs to risks like CoT-hijacking and prompt-induced issues.
Maximilian Mozes, Xuanli He, Bennett Kleinberg, and Lewis D Griffin
5 Pith papers cite this work, alongside 29 external citations. Polarity classification is still indexing.
5
Pith papers citing it
29
external citations · external index
representative citing papers
A new segment-level coherence probing method improves true-positive rate for harmful intent detection by 35.55% at 1% false-positive rate and maintains high AUROC on obfuscated attacks.
StarCoder2-15B matches or beats CodeLlama-34B on code tasks despite being smaller, and StarCoder2-3B outperforms prior 15B models, with open weights and exact training data identifiers released.
A modified Llama 3 model using fully homomorphic encryption achieves up to 98% text generation accuracy and 80 tokens per second at 237 ms latency on an i9 CPU.
citing papers explorer
-
Red Teaming Large Reasoning Models
RT-LRM benchmark finds Large Reasoning Models more fragile than standard LLMs to risks like CoT-hijacking and prompt-induced issues.
-
Segment-Level Coherence for Robust Harmful Intent Probing in LLMs
A new segment-level coherence probing method improves true-positive rate for harmful intent detection by 35.55% at 1% false-positive rate and maintains high AUROC on obfuscated attacks.
-
StarCoder 2 and The Stack v2: The Next Generation
StarCoder2-15B matches or beats CodeLlama-34B on code tasks despite being smaller, and StarCoder2-3B outperforms prior 15B models, with open weights and exact training data identifiers released.
-
Fully Homomorphic Encryption on Llama 3 model for privacy preserving LLM inference
A modified Llama 3 model using fully homomorphic encryption achieves up to 98% text generation accuracy and 80 tokens per second at 237 ms latency on an i9 CPU.
- CaliDist: Calibrating Large Language Models via Behavioral Robustness to Distraction