A repo lists papers about LLM role playing, memory mechanism and LLM game playing.

• AI-Text-Dection

  • [2023/07/30] A Private Watermark for Large Language Models | [paper] | [code]

  • [2023/07/29] Towards Codable Text Watermarking for Large Language Models | [paper] | [code]

  • [2023/07/28] Robust Distortion-free Watermarks for Language Models | [paper] | [code]

  • [2023/07/26] Three Bricks to Consolidate Watermarks for Large Language Models | [paper] | [code]

  • [2023/06/30] Provable Robust Watermarking for AI-Generated Text | [paper] | [code]

  • [2023/06/07] On the Reliability of Watermarks for Large Language Models | [paper] | [code]

  • [2023/05/24] Who Wrote this Code? Watermarking for Code Generation | [paper] | [code]

  • [2023/05/24] M4: Multi-generator, Multi-domain, and Multi-lingual Black-Box Machine-Generated Text Detection | [paper] | [code]

  • [2023/05/24] LLMDet: A Large Language Models Detection Tool | [paper] | [code]

  • [2023/05/23] DetectLLM: Leveraging Log Rank Information for Zero-Shot Detection of Machine-Generated Text | [paper] | [code]

  • [2023/05/22] Deepfake Text Detection in the Wild | [paper] | [code]

  • [2023/05/17] Smaller Language Models are Better Black-box Machine-Generated Text Detectors | [paper] | [code]

  • [2023/05/14] Watermarking Text Generated by Black-Box Language Models | [paper] | [code]

  • [2023/05/05] Evading Watermark based Detection of AI-Generated Content | [paper] | [code]

  • [2023/04/27] Origin Tracing and Detecting of LLMs | [paper] | [code]

  • [2023/03/26] MGTBench: Benchmarking Machine-Generated Text Detection | [paper] | [code]

  • [2023/03/17] Can AI-Generated Text be Reliably Detected? | [paper] | [code]

  • [2023/02/06] Protecting Language Generation Models via Invisible Watermarking | [paper] | [code]

  • [2023/01/26] DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature | [paper] | [code]

  • [2023/01/24] A Watermark for Large Language Models | [paper] | [code]