Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models

• URL: http://arxiv.org/abs/2506.06395v3
• Date: Wed, 11 Jun 2025 06:21:59 GMT
• Title: Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models
• Abstract summary: We propose Reinforcement Learning via Self-Confidence (RLSC) for large language models (LLMs)<n>RLSC uses the model's own confidence as reward signals-eliminating the need for labels, preference models, or reward engineering.
• Score: 43.98994504606355
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) excel at reasoning, yet post-training remains critical for aligning their behavior with task goals. Existing reinforcement learning (RL) methods often depend on costly human annotations or external reward models. We propose Reinforcement Learning via Self-Confidence (RLSC), which uses the model's own confidence as reward signals-eliminating the need for labels, preference models, or reward engineering. Applied to Qwen2.5-Math-7B with only 16 samples per question and 10 or 20 training steps, RLSC improves accuracy by +13.4% on AIME2024, +21.2% on MATH500, +21.7% on Minerva Math, +20.8% on Olympiadbench, and +9.7% on AMC23. RLSC provides a simple, scalable post-training method for inference models, requiring only a small number of samples and unlabelled supervision.

Related papers

• Models for minimalist RAG: B1ade 335M Embedding and 1B Parameter Small Language Models [2.1665689529884697]
  We present B1ade, an efficient RAG architecture comprising two purpose-built components: a compact embedding model and a purpose-built SLM.<n>B1ade-embed, a 335M parameter retrieval model constructed via parameter-free fusion of five pretrained encoders achieves top MTEB scores among sub-500M models with zero additional training.<n>B1ade-1B cites retrieved passages in 42.4% of responses, exceeding the attribution rate of its training distribution by 5.5 percentage points.
  arXiv  Detail & Related papers  (2026-07-29T22:41:25Z)
• OdysSim: Building Foundation Models for Human Behavior Simulation [70.35265860287608]
  Large language models are increasingly deployed as human simulators for interactive evaluation and social simulation.<n>Yet helpfulness-driven post-training pulls them toward a homogeneous, overly agreeable assistant register.<n>We present OdysSim, the largest open systematic investigation of behavioral foundation models.
  arXiv  Detail & Related papers  (2026-06-12T07:31:55Z)
• PRISM: Demystifying Retention and Interaction in Mid-Training [20.198164159173647]
  PRISM is a comprehensive empirical study of mid-training design choices for large language models.<n>We show that mid-training on approximately 27B high-quality tokens yields consistent gains of +15 to +40 points on math, +5 to +12 points on code, and +6 to +13 points on science benchmarks while preserving general performance.
  arXiv  Detail & Related papers  (2026-03-17T19:04:33Z)
• TraPO: A Semi-Supervised Reinforcement Learning Framework for Boosting LLM Reasoning [33.47825979936341]
  Reinforcement learning with verifiable rewards (RLVR) has proven effective in training large reasoning models (LRMs)<n>We propose an effective policy optimization algorithm, TraPO, that identifies reliable unlabeled samples by matching their learning trajectory similarity to labeled ones.<n>With only 1K labeled and 3K unlabeled samples, TraPO reaches 42.6% average accuracy, surpassing the best unsupervised method trained on 45K unlabeled samples (38.3%)
  arXiv  Detail & Related papers  (2025-12-15T09:03:45Z)
• SPARK: Stepwise Process-Aware Rewards for Reference-Free Reinforcement Learning [39.1720897614261]
  Process reward models (PRMs) that provide dense, step-level feedback have shown promise for reinforcement learning.<n>We propose SPARK: a three-stage framework where in the first stage a generator model produces diverse solutions and a verifier model evaluates them.<n>We show that aggregating multiple independent verifications at the step level produces training data for process reward models that surpass ground-truth outcome supervision.
  arXiv  Detail & Related papers  (2025-12-02T21:30:47Z)
• Every Step Evolves: Scaling Reinforcement Learning for Trillion-Scale Thinking Model [100.86587937568832]
  Ring-1T is the first open-source, state-of-the-art thinking model with a trillion-scale parameter.<n>It features 1 trillion total parameters and activates approximately 50 billion per token.
  arXiv  Detail & Related papers  (2025-10-21T17:46:14Z)
• MobileLLM-R1: Exploring the Limits of Sub-Billion Language Model Reasoners with Open Training Recipes [60.57770396565211]
  We show that strong reasoning abilities can emerge with far less data.<n>MobileLLM-R50M achieves an AIME score of 15.5, compared to just 0.6 for OLMo-2-1.48B and 0.3 for SmolLM-2-1.7B.
  arXiv  Detail & Related papers  (2025-09-29T15:43:59Z)
• RLEP: Reinforcement Learning with Experience Replay for LLM Reasoning [18.62575670251997]
  Reinforcement learning (RL) for large language models is an energy-intensive endeavor.<n>We present emphRLEP, a framework that first collects verified trajectories and then replays them during subsequent training.<n>At every update step, the policy is optimized on mini-batches that blend newly generated rollouts with replayed successes.
  arXiv  Detail & Related papers  (2025-07-10T05:58:55Z)
• Resa: Transparent Reasoning Models via SAEs [14.617192915344349]
  SAE-Tuning is a family of 1.5B reasoning models trained via a novel and efficient sparse autoencoder tuning procedure.<n>When applied to certain base models before further RL post-training, SAE-Tuning retains >97% of its RL-trained counterpart's reasoning performance.<n>It enables reasoning performance such as 43.33% Pass@1 on AIME24 and 90% Pass@1 on AMC23 for only around $1 additional cost.
  arXiv  Detail & Related papers  (2025-06-11T17:44:01Z)
• R1-Code-Interpreter: LLMs Reason with Code via Supervised and Multi-stage Reinforcement Learning [23.795932850992816]
  We present R1-Code-Interpreter, an extension of a text-only Large Language Models (LLMs) trained via multi-turn supervised fine-tuning (SFT) and reinforcement learning (RL)<n>We show that training a general-purpose Code Interpreter across 144 diverse reasoning and planning tasks presents significant challenges due to task heterogeneity and scarcity of effective samples.<n>Our final model, R1-CI-14B, improves average accuracy on the 37 test tasks from 44.1% to 72.4%, outperforming text-only GPT-4o (58.6%) and GPT-4o with Code Interpreter (70.9%).
  arXiv  Detail & Related papers  (2025-05-27T18:47:33Z)
• AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning [50.02117478165099]
  We show that large-scale reinforcement learning can significantly enhance the reasoning capabilities of strong, small- and mid-sized models.<n>We propose a simple yet effective approach: first training on math-only prompts, then on code-only prompts.
  arXiv  Detail & Related papers  (2025-05-22T08:50:47Z)
• RM-R1: Reward Modeling as Reasoning [81.50471199906738]
  Reasoning Reward Models (ReasRMs) formulate reward modeling as a reasoning task.<n>We propose a reasoning-oriented training pipeline and train a family of ReasRMs, RM-R1.<n>Our models achieve state-of-the-art performance across three reward model benchmarks on average.
  arXiv  Detail & Related papers  (2025-05-05T06:11:12Z)
• Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models [1.96238419451815]
  Large language models (LLMs) have demonstrated strong capabilities in programming and mathematical reasoning tasks, but are constrained by limited high-quality training data.<n>We introduce a scalable framework that iteratively fine-tunes models on their own reasoning traces, using ground-truth pruning to ensure high-quality training data.<n>This approach yields improved performance: on GSM8K, Gemma2-2B achieves a Pass@1 of 57.6% (from 41.9%), Gemma2-9B reaches 82%, matching LLaMA-3.1-70B, and LLaMA-3.1-70B attains 91%, even surpassing GPT-4o
  arXiv  Detail & Related papers  (2025-04-25T06:48:55Z)
• SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild [46.25416990387885]
  Long chain-of-thought (CoT) reasoning can naturally emerge through a simple reinforcement learning framework with rule-based rewards.<n>We investigate zero RL training across 10 diverse base models including LLama3-8B, Mistral-7B/24B, DeepSeek-Math-7B, Qwen2.5-math-7B, and all Qwen2.5 models from 0.5B to 32B.
  arXiv  Detail & Related papers  (2025-03-24T17:06:10Z)
• LIMR: Less is More for RL Scaling [25.477841726836836]
  We introduce Learning Impact Measurement (LIM), an automated method to evaluate and prioritize training samples.<n>Our method achieves comparable or even superior performance using only 1,389 samples versus the full 8,523 samples dataset.<n>For reproducible research and future innovation, we are open-sourcing LIMR, including implementation of LIM, training and evaluation code, curated datasets, and trained models.
  arXiv  Detail & Related papers  (2025-02-17T15:13:29Z)
• Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning [65.2421542320293]
  Reasoning abilities are crucial components of general intelligence.<n>Recent advances by proprietary companies, such as o-series models of OpenAI, have made remarkable progress on reasoning tasks.<n>This paper proposes a new RL framework, termed OREAL, to pursue the performance limit that can be achieved through textbfOutcome textbfREwtextbfArd-based reinforcement textbfLearning for mathematical reasoning tasks.
  arXiv  Detail & Related papers  (2025-02-10T18:57:29Z)
• Common 7B Language Models Already Possess Strong Math Capabilities [61.61442513067561]
  This paper shows that the LLaMA-2 7B model with common pre-training already exhibits strong mathematical abilities. The potential for extensive scaling is constrained by the scarcity of publicly available math questions.
  arXiv  Detail & Related papers  (2024-03-07T18:00:40Z)
• Improving Large Language Models via Fine-grained Reinforcement Learning with Minimum Editing Constraint [104.53687944498155]
  Reinforcement learning (RL) has been widely used in training large language models (LLMs) We propose a new RL method named RLMEC that incorporates a generative model as the reward model. Based on the generative reward model, we design the token-level RL objective for training and an imitation-based regularization for stabilizing RL process.
  arXiv  Detail & Related papers  (2024-01-11T17:58:41Z)
• LIMA: Less Is More for Alignment [112.93890201395477]
  We train LIMA, a 65B parameter LLaMa language model fine-tuned with the standard supervised loss on only 1,000 carefully curated prompts and responses. LIMA demonstrates remarkably strong performance, learning to follow specific response formats from only a handful of examples. In a controlled human study, responses from LIMA are either equivalent or strictly preferred to GPT-4 in 43% of cases.
  arXiv  Detail & Related papers  (2023-05-18T17:45:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.