method
active
method:low-rank-adaptation-loraLow-Rank Adaptation (LoRA)
Parameter-efficient fine-tuning method used to implement SOO fine-tuning on LLMs
Neighborhood — ranked by edge-count
Frameworks (1)
framework
- The central framework proposed in this paper: aligning AI internal representations of self and others to reduce deceptive behavior
Methods (1)
method
- LoRA (Low-Rank Adaptation)same_asParameter-efficient fine-tuning method used for both SDF and expert iteration stages.
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.
- E2 finding showing CoT's limited benefit for OOD transfer, consistent with larger dr out of scope
- Specific fine-tuning implementation using LoRA rank 32, learning rate 2e-4, AdamW 8-bit optimizer
- Fine-tuning with chain-of-thought rationales aiming to reduce dr via procedural alignment.
- The ultimate goal of participation: an environment so deeply fitted to its users that genuine satisfaction and life emerge
- Weathering, leaning, and environmental adaptation that gives a fence or object more life.
- The principle that decision-making about centers must be decentralized to the people closest to them to achieve a living environment.
- Central theoretical puzzle in ETI research: explains why existing frameworks struggle with ETI explanation.
- Contrast with Magnum shows LoRA vs full fine-tuning difference in residual headroom