# Post-Completion Learning for Language Models

arXiv: https://arxiv.org/abs/2507.20252 · HTML: https://mlsanity.com/paper/2507.20252/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 33 references that are in the map.
- First posted on arXiv 27 Jul 2025.

## Builds on (most cited first, 24 of 24)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Solving math word problems with process- and outcome-based feedback](https://mlsanity.com/paper/2211.14275/) (2022)
- [Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies](https://mlsanity.com/paper/2101.02235/) (2021)
- [The Lessons of Developing Process Reward Models in Mathematical Reasoning](https://mlsanity.com/paper/2501.07301/) (2025)
- [When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMs](https://mlsanity.com/paper/2406.01297/) (2024)
- [Spurious Rewards: Rethinking Training Signals in RLVR](https://mlsanity.com/paper/2506.10947/) (2025)
- [Self-Improvement in Language Models: The Sharpening Mechanism](https://mlsanity.com/paper/2412.01951/) (2024)
- [SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoning](https://mlsanity.com/paper/2506.19767/) (2025)
- [Q-SFT: Q-Learning for Language Models via Supervised Fine-Tuning](https://mlsanity.com/paper/2411.05193/) (2024)

## Built on by (most cited first, 3 of 3)

- [A Survey of Reinforcement Learning for Large Reasoning Models](https://mlsanity.com/paper/2509.08827/) (2025)
- [MirageBackdoor: A Stealthy Attack that Induces Think-Well-Answer-Wrong Reasoning](https://mlsanity.com/paper/2604.06840/) (2026)
- [Self-Evaluation Is Already There: Eliciting Latent Judge Calibration in Base LLMs with Minimal Data](https://mlsanity.com/paper/2606.05122/) (2026)

## Abstract (arXiv)

Current language model training paradigms typically terminate learning upon reaching the end-of-sequence (<eos>) token, overlooking the potential learning opportunities in the post-completion space. We propose Post-Completion Learning (PCL), a novel training framework that systematically utilizes the sequence space after model output completion, to enhance both the reasoning and self-evaluation abilities. PCL enables models to continue generating self-assessments and reward predictions during training, while maintaining efficient inference by stopping at the completion point. To fully utilize this post-completion space, we design a white-box reinforcement learning method: let the model evaluate the output content according to the reward rules, then calculate and align the score with the reward functions for supervision. We implement dual-track SFT to optimize both reasoning and evaluation capabilities, and mixed it with RL training to achieve multi-objective hybrid optimization. Experimental results on different datasets and models demonstrate consistent improvements over traditional SFT and RL methods. Our method provides a new technical path for language model training that enhances output quality while preserving deployment efficiency.