AdaJudge: Adaptive Multi-Perspective Judging for Reward Modeling
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's optimization for generation leaves its representations ill-suited to fine-grained discrimination. To address this, we propose AdaJudge, a unified framework that jointly adapts representation and aggregation. AdaJudge first improves backbone representations into a discrimination-oriented space via gated refinement blocks. It then replaces the static readout with an adaptive multi-view pooling module, which 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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Better Language Model-Based Judging Reward Modeling through Scaling Comprehension Boundaries
The emergence of LM-based judging reward modeling, represented by generative reward models, has successfully made reinforcement learning from AI feedback (RLAIF) efficient and scalable. To further advance this paradigm, …
Natural Language UnderstandingNatural Language InferenceReinforcement LearningSAIL-RL: Guiding MLLMs in When and How to Think via Dual-Reward RL Tuning
We introduce SAIL-RL, a reinforcement learning (RL) post-training framework that enhances the reasoning capabilities of multimodal large language models (MLLMs) by teaching them when and how to think. Existing approaches…
Reinforcement LearningJudging with Many Minds: Do More Perspectives Mean Less Prejudice?
LLM-as-Judge has emerged as a scalable alternative to human evaluation, enabling large language models (LLMs) to provide reward signals in trainings. While recent work has explored multi-agent extensions such as multi-ag…
FairJudge: An Adaptive, Debiased, and Consistent LLM-as-a-Judge
Existing LLM-as-a-Judge systems suffer from three fundamental limitations: limited adaptivity to task- and domain-specific evaluation criteria, systematic biases driven by non-semantic cues such as position, length, form…
ARBOR: Online Process Rewards via a Reusable Rubric Buffer for Search Agents
LLM-based search agents are trained predominantly with outcome-only reward, leaving the search process itself unsupervised. This signal degenerates on outcome-homogeneous groups where all sampled trajectories share the s…