Inverse Turing Bench evaluates LLMs on distinguishing human-human from human-AI dialogues, with GPTZero at 89.41%, Claude Opus-4.6 at 77.92%, and GPT-5.5 at 75.94% accuracy.
InProceedings of the 2024 ACM SIGSAC Conference on Computer and Communications Security (CCS ’24)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
ICL4Decomp applies in-context learning to guide LLMs in generating re-executable decompiled code from binaries, reporting roughly 40% higher re-executability than prior methods across datasets and optimization levels.
citing papers explorer
-
Inverse Turing Bench: Evaluating Language Models as Judges of Human vs. AI Dialogue
Inverse Turing Bench evaluates LLMs on distinguishing human-human from human-AI dialogues, with GPTZero at 89.41%, Claude Opus-4.6 at 77.92%, and GPT-5.5 at 75.94% accuracy.
-
Context-Guided Decompilation: A Step Towards Re-executability
ICL4Decomp applies in-context learning to guide LLMs in generating re-executable decompiled code from binaries, reporting roughly 40% higher re-executability than prior methods across datasets and optimization levels.