{
  "annotation_id": "6ee473c9-112e-4c3f-9681-16b2717fd80d",
  "date_created": "2026-02-17T05:53:16.065000Z",
  "date_modified": "2026-02-17T05:53:16.065000Z",
  "file_hash": "926e18b811a9bf851840f6284f2718f2a05e602a71b5e72d1b88f21fb477f381",
  "private": false,
  "record": {
    "abstract": "Reward modeling is essential for aligning large language models with human preferences, yet predominant architectures rely on a static pooling strategy to condense sequences into scalar scores. This paradigm, however, suffers from two key limitations: a static inductive bias that misaligns with task-dependent preference signals, and a representational mismatch, as the backbone is optimized for generation rather than fine-grained discrimination. To address this, we propose AdaJudge, a unified framework that jointly adapts representation and aggregation. AdaJudge first refines backbone representations into a discrimination-oriented space via gated refinement blocks. It then replaces the static readout with an adaptive multi-view pooling module that dynamically routes and combines evidence. Extensive experiments on RM-Bench and JudgeBench show that AdaJudge outperforms strong off-the-shelf reward models and traditional pooling baselines.",
    "arxiv_id": "2601.08097",
    "authors": [
      "Yongliang Miao",
      "Yangyang Liang",
      "Mengnan Du"
    ],
    "categories": [
      "cs.CL",
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "title": "AdaJudge: Adaptive Multi-Perspective Judging for Reward Modeling",
    "url": "https://arxiv.org/abs/2601.08097",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "b1f3db84-02ca-4efb-998b-7c2f9dfa23be",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}