arXiv AI By Qiming Bao, Juho Leinonen, Paul Denny, Michael J. Witbrock

RLearner-LLM: Balancing Logical Grounding and Fluency in Large Language Models via Hybrid Direct Preference Optimization

Read the original on arXiv AI →

arXiv:2605. 04539v4 Announce Type: replace-cross Abstract: Direct Preference Optimization (DPO), the efficient alternative to PPO-based RLHF, falls short on knowledge-intensive generation: standard preference signals from human annotators or LLM judges exhibit a systematic verbosity bias that rewards fluency over logical correctness.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI
Jun 26

NebulaExp-8B: An Empirical Post-Training Pipeline via Full-Scale Ablation Research

arXiv:2606. 26671v1 Announce Type: new Abstract: Post-training alignment determines the reasoning and human preference following capabilities of large language models, yet most existing works withhold detailed data construction, filtering rules and training recipes, which hinders community reproducibility and lightweight model optimization.

By Qiaobo Hao, Yangqian Wu, Shunyi Wang, Zhongjian Zhang, Ziqun Li, Yayin He, Muqing Li, Chen Zhong
arXiv AI
Aug 12

RLMOpt: Adaptive Prompt Optimization via Recursive Language Models

arXiv:2608. 10471v1 Announce Type: new Abstract: Prompt optimizers automate the search for prompts that improve language-model performance, but existing methods rely on a predefined optimization procedure: the algorithm determines which candidates to explore and how the search progresses, while the language model generates or refines prompt proposals.

By Subhash Bangalore Satheesha, Nirvik Pande, Deepthi Duddempudi, Bharath Dandala
arXiv AI
Jul 17

HABIB_TAZ at SemEval-2026 Task 11: Disentangling Formal Logic from Content via Synthetic Training and Multi-Objective Optimization

arXiv:2607. 14349v1 Announce Type: cross Abstract: While Large Language Models (LLMs) excel in many general NLP tasks, their formal reasoning capabilities are often compromised by content effects, demonstrating a measurable bias towards real-world plausibility.

By Abdullah Shaikh, Zain Naqi, Taha Zahid, Sandesh Kumar, Abdul Samad