Arash Ahmadi, Sarah Sharif, Yaser, Banad · May 3, 2026 · Citations: 0
Pairwise Preference Automatic Metrics Math
- Mathematical reasoning is a key benchmark for large language models.
← Back to explorer Enhanced LLM Reasoning by Optimizing Reward Functions with Search-Driven Reinforcement Learning ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning SSG: Logit-Balanced Vocabulary Partitioning for LLM Watermarking Removing Sandbagging in LLMs by Training with Weak Supervision Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text Don't Overthink It: Inter-Rollout Action Agreement as a Free Adaptive-Compute Signal for LLM Agents Cognitive Loop of Thought: Reversible Hierarchical Markov Chain for Efficient Mathematical Reasoning How Long Reasoning Chains Influence LLMs' Judgment of Answer Factuality SHAPE: Stage-aware Hierarchical Advantage via Potential Estimation for LLM Reasoning Exclusive Unlearning QED-Nano: Teaching a Tiny Model to Prove Hard Theorems From High-Dimensional Spaces to Verifiable ODD Coverage for Safety-Critical AI-based Systems RuleForge: Automated Generation and Validation for Web Vulnerability Detection at Scale S0 Tuning: Zero-Overhead Adaptation of Hybrid Recurrent-Attention Models Brainstacks: Cross-Domain Cognitive Capabilities via Frozen MoE-LoRA Stacks for Continual LLM Learning TRIMS: Trajectory-Ranked Instruction Masked Supervision for Diffusion Language Models Agent Q-Mix: Selecting the Right Action for LLM Multi-Agent Systems through Reinforcement Learning Hierarchical Chain-of-Thought Prompting: Enhancing LLM Reasoning Performance and Efficiency Learning to Predict Future-Aligned Research Proposals with Language Models RASPRef: Retrieval-Augmented Self-Supervised Prompt Refinement for Large Reasoning Models
Tag: Math
Math evaluation papers that call for domain expertise or specialist review (141 papers).
Papers in tag: 141
Need Math evaluators for your project?
Post a Job →Research Utility Snapshot
Evaluation Modes
- Automatic Metrics (13)
- Human Eval (2)
- Llm As Judge (1)
Human Feedback Types
- Expert Verification (2)
- Pairwise Preference (2)
- Rubric Rating (2)
Required Expertise
- Math (20)
- Coding (10)
- Law (1)
Zihan Lin, Xiaohan Wang, Jie Cao, Jiajun Chai, Li Wang, Xiaodong Lu · May 1, 2026 · Citations: 0
Automatic Metrics MathCoding
- ResRL then projects negative-token hidden representations onto an SVD-based low-rank positive subspace and uses projection residuals to modulate negative gradients, improving reasoning while preserving diversity and outperforming strong…
Chenxi Gu, Xiaoning Du, John Grundy · Apr 24, 2026 · Citations: 0
Pairwise Preference MathCoding
- A crucial step in the KGW method is random vocabulary partitioning, which enables adjustments to token selection based on specific preferences.
Emil Ryd, Henning Bartsch, Julian Stastny, Joe Benton, Vivek Hebbar · Apr 23, 2026 · Citations: 0
Demonstrations MathCoding
- As AI systems begin to automate complex tasks, supervision increasingly relies on weaker models or limited human oversight that cannot fully verify output quality.
Chengyu Huang, Sheng-Yen Chou, Zhengxin Zhang, Claire Cardie · Apr 21, 2026 · Citations: 0
Rubric Rating MathCoding
- A key benefit of self-play for post-training LLMs is its minimal supervision costs: self-play avoids the need for high-quality input-output pairs traditionally constructed by humans or expensive proprietary models.
- We propose POP, a self-play framework that uses the same LLM to synthesize evaluation rubrics along with each input-output pair.
Khushal Sethi · Apr 9, 2026 · Citations: 0
Automatic Metrics Math
- We introduce TrACE (Trajectorical Adaptive Compute via agrEement), a training-free controller that allocates LLM calls adaptively across agent timesteps by measuring inter-rollout action agreement.
- We evaluate TrACE against greedy decoding and fixed-budget self-consistency (SC-4, SC-8) on two benchmarks spanning single-step reasoning (GSM8K, n=50) and multi-step household navigation (MiniHouse, n=30), using a Qwen 2.5 3B Instruct…
Jia-Chen Zhang, Yu-Jie Xiong, Zheng Zhou · Apr 8, 2026 · Citations: 0
Automatic Metrics Math
- Inspired by human cognitive processes, we introduce a backward verification mechanism at each hierarchical layer.
- Experiments on four mathematical benchmarks demonstrate the effectiveness of our method.
Minzhu Tu, Shiyu Ni, Keping Bi · Apr 8, 2026 · Citations: 0
Human EvalAutomatic Metrics Math
- Large language models (LLMs) has been widely adopted as a scalable surrogate for human evaluation, yet such judges remain imperfect and susceptible to surface-level biases.
- With the rise of reasoning-capable models, exposing a generator's reasoning content to the judge provides richer information and is a natural candidate for improving judgment accuracy.
Zhengyang Ai, Zikang Shan, Xiaodong Ai, Jingxian Tang, Hangkai Hu, Pinyan Lu · Apr 8, 2026 · Citations: 0
Automatic Metrics Math
- Extensive experiments in math reasoning across three base models and five benchmarks demonstrate that SHAPE achieves an average accuracy gain of 3% with 30% reduced token consumption.
Mutsumi Sasaki, Kouta Nakayama, Yusuke Miyao, Yohei Oseki, Masaru Isonuma · Apr 7, 2026 · Citations: 0
Red Team Math
- We demonstrate that through Exclusive Unlearning, it is possible to obtain a model that ensures safety against a wide range of inputs, including jailbreaks, while maintaining the ability to respond to diverse instructions related to…
LM-Provers, Yuxiao Qu, Amrith Setlur, Jasper Dekoninck, Edward Beeching, Jia Li · Apr 6, 2026 · Citations: 0
Rubric Rating Automatic Metrics MathCoding
- To support further research on open mathematical reasoning, we release the full QED-Nano pipeline, including the QED-Nano and QED-Nano-SFT models, the FineProofs-SFT and FineProofs-RL datasets, and the training and evaluation code.
Thomas Stefani, Johann Maximilian Christensen, Elena Hoemann, Frank Köster, Sven Hallerbach · Apr 2, 2026 · Citations: 0
Simulation Env Math
- While Artificial Intelligence (AI) offers transformative potential for operational performance, its deployment in safety-critical domains such as aviation requires strict adherence to rigorous certification standards.
- Ultimately, this method enables the validation of ODD coverage in higher dimensions, advancing a Safety-by-Design approach while complying with EASA's standards.
Ayush Garg, Sophia Hager, Jacob Montiel, Aditya Tiwari, Michael Gentile, Zach Reavis · Apr 2, 2026 · Citations: 0
Expert Verification Llm As JudgeAutomatic Metrics Math
- This paper focuses on RuleForge's architecture and operational deployment for CVE-related threat detection, with particular emphasis on our novel LLM-as-a-judge (Large Language Model as judge) confidence validation system and systematic…
- We also present extensions enabling rule generation from unstructured data sources and demonstrate a proof-of-concept agentic workflow for multi-event-type detection.
Jack Young · Apr 1, 2026 · Citations: 0
Automatic Metrics MathCoding
- Using roughly 48 execution-verified HumanEval training solutions, tuning a single initial state matrix per recurrent layer, with zero inference overhead, outperforms LoRA by +10.8 pp (p < 0.001) on HumanEval.
- Cross-domain transfer is significant on MATH-500 (+4.8 pp, p = 0.00002, 8 seeds) and GSM8K (+2.8 pp, p = 0.0003, 10 seeds); a text-to-SQL benchmark (Spider) shows no transfer, consistent with the trajectory-steering mechanism.
Mohammad R. Abu Ayyash · Apr 1, 2026 · Citations: 0
Expert Verification MathMedicine
Lingjie Chen, Ruizhong Qiu, Yuyu Fan, Yanjun Zhao, Hanghang Tong · Apr 1, 2026 · Citations: 0
Automatic Metrics MathCoding
- Experiments on LLaDA and Dream across math and coding benchmarks show that TRIMS significantly improves the accuracy-parallelism trade-off over both standard MDLM training and train-free acceleration baselines, while achieving competitive…
Eric Hanchen Jiang, Levina Li, Rui Sun, Xiao Liang, Yubei Li, Yuchen Wu · Apr 1, 2026 · Citations: 0
Automatic Metrics MathLaw
- In this paper, we propose Agent Q-Mix, a reinforcement learning framework that reformulates topology selection as a cooperative Multi-Agent Reinforcement Learning (MARL) problem.
- Across seven core benchmarks in coding, reasoning, and mathematics, Agent Q-Mix achieves the highest average accuracy compared to existing methods while demonstrating superior token efficiency and robustness against agent failure.
Xingshuai Huang, Derek Li, Bahareh Nikpour, Parsa Omidi · Mar 31, 2026 · Citations: 0
Automatic Metrics MathCoding
- Extensive evaluations across diverse LLMs and mathematical reasoning benchmarks show that Hi-CoT consistently improves average accuracy by 6.2% (up to 61.4% on certain models and tasks) while reducing reasoning trace length by 13.9%…
Heng Wang, Pengcheng Jiang, Jiashuo Sun, Zhiyi Shi, Haofei Yu, Jiawei Han · Mar 28, 2026 · Citations: 0
Human EvalAutomatic Metrics MathCoding
- Across Llama-3.1 and Qwen2.5 models, future-aligned tuning improves future alignment over unaligned baselines (up to +10.6% overall FAS), and domain-expert human evaluation corroborates improved proposal quality.
- Finally, we demonstrate practical impact by implementing two model-generated proposals with a code agent, obtaining 4.17% accuracy gain on MATH from a new prompting strategy and consistent improvements for a novel model-merging method.
Rahul Soni · Mar 27, 2026 · Citations: 0
Critique Edit Math
- Recent reasoning-focused language models such as DeepSeek R1 and OpenAI o1 have demonstrated strong performance on structured reasoning benchmarks including GSM8K, MATH, and multi-hop question answering tasks.
- To address this limitation, we introduce Retrieval-Augmented Self-Supervised Prompt Refinement (RASPRef), a framework that improves prompts without requiring human annotations or task-specific supervision.