HFEPX · Eval paper review
Changho Lee, Janghoon Han, Rajdeep Mukherjee, Yeda Song +3 more
Published
Oct 18, 2026
Citations
0
Trust level
Low
Usefulness score
0/100 (Low)
Extraction confidence
20% (Low)
Derived from extracted protocol signals and abstract evidence.
Rater population
Not reported
Signals refreshed
Oct 18, 2026
This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.
Use this as background context only. Do not make protocol decisions from this page alone.
All signals on this page are inferred from the abstract only and may be inaccurate. Do not use this page as a primary protocol reference.
Best use
Background context only
Use if you need
Background context only.
What to verify
Validate the evaluation procedure and quality controls in the full paper before operational use.
Main weakness
This paper looks adjacent to evaluation work, but not like a strong protocol reference.
Treat as adjacent context, not a core eval-method reference.
If you are doing eval pipeline work, start here
Reasoning post-training on long trajectories has substantially improved the reasoning capabilities of large language models, but scaling such training to large datasets is increasingly expensive. We study target-aware reasoning data selection, where a small reference set specifies a target capability and guides the selection of training trajectories for specialization. We find that existing target-aware methods can exhibit limited target discrimination on long reasoning trajectories, while dominant population-level structure in candidate gradients can obscure finer target-dependent variation during gradient matching. To address these limitations, we introduce Deconfounded Gradient Matching (DeGMatch), which first constructs a target-relevance gate and then reranks candidates using model-specific gradients. DeGMatch centers gradients using the candidate-population mean and removes leading principal directions before target matching, reducing the influence of dominant population-level structure and improving target discrimination. Across mathematics, science, and code, DeGMatch outperforms strong heuristic, target-aware, and reasoning-specific data selection baselines, while remaining effective across selection budgets, model families, and scales. Our code is publicly available at https://github.com/CHLee0801/degmatch.
These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.
None explicit
No explicit feedback protocol extracted.
"Reasoning post-training on long trajectories has substantially improved the reasoning capabilities of large language models, but scaling such training to large datasets is increasingly expensive."
None explicit
Validate eval design from full paper text.
"Reasoning post-training on long trajectories has substantially improved the reasoning capabilities of large language models, but scaling such training to large datasets is increasingly expensive."
Not reported
No explicit QC controls found.
"Reasoning post-training on long trajectories has substantially improved the reasoning capabilities of large language models, but scaling such training to large datasets is increasingly expensive."
Not extracted
No benchmark anchors detected.
"Reasoning post-training on long trajectories has substantially improved the reasoning capabilities of large language models, but scaling such training to large datasets is increasingly expensive."
Relevance
Useful for evaluation criteria comparison.
"To address these limitations, we introduce Deconfounded Gradient Matching (DeGMatch), which first constructs a target-relevance gate and then reranks candidates using model-specific gradients."
No benchmark or dataset names were extracted from the available abstract.
Reasoning post-training on long trajectories has substantially improved the reasoning capabilities of large language models, but scaling such training to large datasets is increasingly expensive.
Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.
Human feedback protocol is explicit
No explicit human feedback protocol detected.
Evaluation mode is explicit
No clear evaluation mode extracted.
Quality control reporting appears
No calibration/adjudication/IAA control explicitly detected.
Benchmark or dataset anchors are present
No benchmark/dataset anchor extracted from abstract.
Metric reporting is present
Detected: relevance
