claim
active
claim:self-supervised-context-prediction-plays-a-role-similar-to-self-supervised-pre-training-in-frontier-llmsSelf-supervised context prediction plays a role similar to self-supervised pre-training in frontier LLMs
Justifies scalability of the task.
Source paper
extracted_from(2025) · Adam Karvonen
Neighborhood — ranked by edge-count
Papers (1)
paper
Methods (1)
method
- Predict preceding or following text from an activation; scalable without labeled data.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- The thesis that transformers develop a self-model via ICL, not only from training data; base models bootstrap self-referential reasoning.
- The paper's claim that theoretical convergence across GWT, RPT, HOT, IIT makes the findings non-coincidental
- Prior finding showing scale-dependent self-awareness, consistent with the scale effect observed in the paper's Experiment 1
- Antra's foundational claim about how introspection arises computationally rather than from memorised text.
- Binder et al. finding cited as evidence that LLMs possess introspective capacity analogous to mindfulness
- does a model's base capability in task-solving predict its capabilities in harness self-evolution?question0.747Central framing question motivating the paper's capability decomposition
- Extension of the thesis to deployed LLM inference via in-context learning
- Comparative prediction motivating future work contrasting different approaches to LLM self-knowledge