Self-Generated Text Recognition: Quality Heuristics, Cross-Task Transfer, and Downstream Bias in LLM Evaluation
cs.CL, cs.AI
Submitted: 2026-07-07
Updated: 2026-08-28
Comments: 31 pages, 9 figures (3 main body, 6 appendix), 18 tables (1 main body, 17 appendix)
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Inspection and Control of Self-Generated-Text Recognition Ability in Llama3-8b-Instruct
- Mitigating Many-Shot Jailbreaking
- Know Thyself? On the Incapability and Implications of AI Self-Recognition
- Taken out of context: On measuring situational awareness in LLMs
- Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference
- Self-Recognition in Language Models
- Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators
- AI Control: Improving Safety Despite Intentional Subversion
- Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
- PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference
- Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)
- Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs
- Preference Leakage: A Contamination Problem in LLM-as-a-judge
- LLM Evaluators Recognize and Favor Their Own Generations
- Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols
- Alignment Pretraining: AI Discourse Causes Self-Fulfilling (Mis)alignment
- Self-Preference Bias in LLM-as-a-Judge
- Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
- BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions
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