Self-Generated Text Recognition: Quality Heuristics, Cross-Task Transfer, and Downstream Bias in LLM Evaluation

arXiv:2608.26159 · cs.CL, cs.AI · Submitted 2026-07-07 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-07-07

Updated: 2026-08-28

Terminology

• Accuracy — 47× in this paper · explained in 1 episode
• LLM-as-a-Judge — 8× in this paper · explained in 3 episodes
• Adversarial Training — 7× in this paper · explained in 1 episode
• Alignment — 7× in this paper · explained in 1 episode
• Benchmark — 6× in this paper · explained in 2 episodes
• Trace — 5× in this paper · explained in 2 episodes
• Fine-Tuning — 4× in this paper · explained in 5 episodes
• Reasoning Traces — 4× in this paper · explained in 3 episodes
• Self-Generated Text Recognition — 4× in this paper
• Adam — 1× in this paper · explained in 2 episodes
• Alignment Problem — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Clustering — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Homogeneity — 1× in this paper · explained in 2 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• LLM judge — 1× in this paper · explained in 2 episodes
• Mentorship for Alignment Research Students — 1× in this paper
• Multi-Agent System — 1× in this paper · explained in 5 episodes
• Situational Awareness Dataset — 1× in this paper
• Structured Reasoning — 1× in this paper · explained in 3 episodes
• Transferability — 1× in this paper · explained in 4 episodes

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