paper-with-me

홈 › Papers

Beyond Reasoning: Reinforcement Learning Unlocks Parametric Knowledge in LLMs

2026-05-08 · Wanli Yang, Hongyu Zang, Junwei Zhang, Wenjie Shi, Du Su, Jingang Wang, Xueqi Cheng, Fei Sun arxiv

Reinforcement learning (RL) has achieved remarkable success in LLM reasoning, but whether it can also improve direct recall of parametric knowledge remains an open question. We study this question in a controlled zero-shot, one-hop, closed-book QA setting with no chain-of-thought, training only on binary correctness rewards and applying fact-level train-test deduplication to ensure gains reflect improved recall rather than reasoning or memorization. Across three model families and multiple factual QA benchmarks, RL yields ~27% average relative gains, surpassing both training- and inference-time baselines alike. Mechanistically, RL primarily redistributes probability mass over existing knowledge rather than acquiring new facts, moving correct answers from the low-probability tail into reliable greedy generations. Our data-attribution study reveals that the hardest examples are the most informative: those whose answers never appear in 128 pre-RL samples (only ~18% of training data) drive ~83% of the gain, since rare correct rollouts still emerge during training and get reinforced. Together, these findings broaden the role of RL beyond reasoning, repositioning it as a tool for unlocking rather than acquiring latent parametric knowledge.

📄 PDF Abstract BibTeX arXiv:2605.07153

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Thinking to Recall: How Reasoning Unlocks Parametric Knowledge in LLMs

2026-03-10 · Zorik Gekhman, Roee Aharoni, Eran Ofek, Mor Geva 외 arxiv

While reasoning in LLMs plays a natural role in math, code generation, and multi-hop factual questions, its effect on simple, single-hop factual questions remains unclear. Such questions do not require step-by-step logic…

Code Generation

Improving Parametric Knowledge Access in Reasoning Language Models

2026-02-25 · Melody Ma, John Hewitt arxiv

We study reasoning for accessing world knowledge stored in a language model's parameters. For example, recalling that Canberra is Australia's capital may benefit from thinking through major cities and the concept of purp…

Reinforcement LearningQuestion AnsweringNatural Questions

Internalizing Meta-Experience into Memory for Guided Reinforcement Learning in Large Language Models

2026-02-10 · Shiting Huang, Zecheng Li, Yu Zeng, Qingnan Ren 외 arxiv

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an effective approach for enhancing the reasoning capabilities of Large Language Models (LLMs). Despite its efficacy, RLVR faces a meta-learning bottle…

Reinforcement Learning

CapTrack: Multifaceted Evaluation of Forgetting in LLM Post-Training

2026-02-19 · Lukas Thede, Stefan Winzeck, Zeynep Akata, Jonathan Richard Schwarz arxiv

Large language model (LLM) post-training enhances latent skills, unlocks value alignment, improves performance, and enables domain adaptation. Unfortunately, post-training is known to induce forgetting, especially in the…

Domain Adaptation

Case-Based Calibration of Adaptive Reasoning and Execution for LLM Tool Use

2026-05-14 · Renning Pang, Tian Lan, Leyuan Liu, Piao Tong 외 arxiv

Tool use extends large language models beyond parametric knowledge, but reliable execution requires balancing appropriate reasoning depth with strict structural validity. We approach this problem from a case-based perspe…

Reinforcement Learning