LegalRewardBench: Benchmarking Reward Models for Legal Preference Evaluation
cs.CL
Submitted: 2026-10-13
Updated: 2026-10-13
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
- SaulLM-7B: A pioneering Large Language Model for Law
- Chatlaw: A Multi-Agent Legal Assistant based on a Role-Aligned Mixture-of-Experts Architecture
- Legal$\Delta$: Enhancing Legal Reasoning in LLMs via Reinforcement Learning with Chain-of-Thought Guided Information Gain
- RLHF Workflow: From Reward Modeling to Online RLHF
- Building Legal Reward Models for Grounding and Abstention
- LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models
- Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains
- RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment
- LegalOne: A Family of Foundation Models for Reliable Legal Reasoning
- Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs
- AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories
- Generative Reward Models
- RewardBench 2: Advancing Reward Model Evaluation
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- IF-RewardBench: Benchmarking Judge Models for Instruction-Following Evaluation
- Qwen3 Technical Report
- Multimodal RewardBench: Holistic Evaluation of Reward Models for Vision Language Models
- A Comprehensive Survey of Reward Models: Taxonomy, Applications, Challenges, and Future
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering