Jasper Dekoninck
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
NLP×1
Frequent co-authors
Research Timeline
2026
Learning from Saturated Data: Signals Beyond Correctness for LLM Training
The paper proposes using fine-grained quality signals, such as pairwise self-judgments and token-level entropy, instead of simple binary correctness to improve LLM performance on saturated datasets, showing significant gains on simple tasks but requiring careful calibration for complex ones.
Highlighted terms show continued research focus across papers