Self-Generated Text Recognition (SGTR)--the ability of an LLM to identify its own outputs--poses risks to AI safeguards that rely on LLMs as evaluators or monitors: an LLM may recognize outputs from other copies of the same model and make biased judgments or collude outright. Prior work has drawn conflicting conclusions about whether current models possess significant SGTR capabilities. We explain these disagreements by identifying key experimental design choices--which we term operationalizations--that drive divergent results. Evaluating 13-21 models across six presentation operationalizations and four task-domain operationalizations, we find that accuracy varies substantially with evaluation format (pairwise vs individual assessments of text), conversation format (presenting candidate text in user tags vs assistant tags), and the domain of the task used to generate candidate text (e.g., coding vs summarization). We corroborate previous observations that a quality heuristic--models attributing authorship to text they perceive as higher quality--is a dominant confound. We also find that improving a model's SGTR performance via supervised fine-tuning (SFT) on one operationalization can generalize to others, and can increase the model's preference for its own outputs when it acts as a judge in the AlpacaEval framework. Our results suggest that, despite confounds, some models possess practical SGTR capabilities, and that SGTR should be monitored and considered in the design of safety-critical AI applications.
J. St-Amand, Callum Canavan, S. Imran et al.· 0 citations
Post-training alignment is often shallow, eroding under fine-tuning. It remains untested as to whether constitutional midtraining interventions can produce durable alignment when cleanly isolated from post-training. We build a 394M-token constitutional corpus from Anthropic's Constitution and apply constitutional midtraining at 120B scale, where principled, values-based content is inserted into midtraining. A 2x2 design (curriculum ordering x deliberative reasoning) was used to produce four constitutionally midtrained conditions, plus a control, which were evaluated on self-generated and established benchmarks including alignment under pressure, value conflict resolution, blackmail, and emergent misalignment. All models were evaluated across three stages: post-midtraining, post-SFT, and post-benign fine-tuning. Constitutionally midtrained models outperformed the control on alignment generalization and durability, notably on blackmail: SFT instilled a blackmail propensity in all models, but constitutional midtraining blunted it, with the advantage surviving benign fine-tuning (-17.5pp). This durability did not extend to settings that required active resistance to in-context pressure or conflict, where the advantage attenuates after SFT. The presence of constitutional content at midtraining also mattered more than its structure, and constitutional midtraining incurred no capability cost, on average, at any stage (MMLU, ARC-Easy, piqa, GSM8K). A modest amount of constitutional content at midtraining could therefore yield broad, persistent alignment gains, offering a cheap, complementary addition to SFT-centered pipelines. Code, data, and models are available.
Desiree Cho, Cameron Tice, Bernie Hogan et al.· 0 citations