ShadowCoT introduces a reasoning-level backdoor attack on LLMs achieving 94.4% attack success rate and 88.4% hijacking success rate with 0.15% parameter updates via internal state conditioning and reasoning chain pollution.
Critic-CoT: Boosting the reasoning abilities of large language model via chain-of-thoughts critic
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Dual-Track CoT lets small language models perform reliable multi-step reasoning with the same or fewer tokens via budget tracking and rejection of redundant steps.
citing papers explorer
-
ShadowCoT: Cognitive Hijacking for Stealthy Reasoning Backdoors in LLMs
ShadowCoT introduces a reasoning-level backdoor attack on LLMs achieving 94.4% attack success rate and 88.4% hijacking success rate with 0.15% parameter updates via internal state conditioning and reasoning chain pollution.
-
Dual-Track CoT: Budget-Aware Stepwise Guidance for Small LMs
Dual-Track CoT lets small language models perform reliable multi-step reasoning with the same or fewer tokens via budget tracking and rejection of redundant steps.