The authors developed Adaptive Tutoring Optimization, a training method intended to improve credit assignment when only a whole document set receives a reward.
Adaptive tutoring helps rerankers assemble better evidence sets for research
AdaTutoRank learns to select complementary, comprehensive and non-redundant documents using quality-matched hints and set-level rewards.
Chinese Tech
Kailin Jiang · Lei Liu · Jian Xi · Yangqi Chen · Hui Xu · Hongwei Zhao · +3 more
University of Science and Technology of China · Yuanbao Team, Tencent
Research Digest··2 min read
Jiang et al.
Why this paper
From Yuanbao Team, Tencent and University of Science and Technology of China · Released code, weights and data
In one line
AdaTutoRank, a setwise reranker with adaptive tutoring hints matched to rollout quality, tops ten RAG and deep research benchmarks while using fewer retrieval calls.
What it released
CodeDataWeights
What we could check
- ✓Code link in the paper (github.com)
- ✓Weights released (huggingface.co)
- ✓Dataset link in the paper (huggingface.co)
- ·No compute details found
- ·No stated limitations found
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§