method
active
method:data-filtering-example-token-levelData Filtering (example/token level)
Remove or downweight units whose preference is explained by a concept.
Neighborhood — ranked by edge-count
Papers (1)
paper
Frameworks (1)
framework
- Unifying framework: remove or amplify a concept's term in the exponential-tilt reward.
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.
- Mitigation technique that filters out datapoints identified by probe-based ranking.
- Poisoning results.
- Averaging acts as a low-pass filter that smooths away per-token detail and retains broad conceptsclaim0.743Intuition.
- Token-level supervision enables models to learn functional-token invocation from reasoning contextclaim0.743ATLAS author's assertion that functional tokens optimized via standard cross-entropy loss learn when and how to invoke operations from surrounding text.
- Strategy of extracting persona vectors from averaged activations over response tokens, found most effective compared to prompt-based positions
- Behavior where information about full clauses is encoded over clause-ending punctuation tokens in LLMs
- §5.5.
- Aggregation of token-level activations.