Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text

• URL: http://arxiv.org/abs/2604.20051v1
• Date: Tue, 21 Apr 2026 23:21:56 GMT
• Title: Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text
• Abstract summary: Self-play has emerged as a promising paradigm to train Large Language Models (LLMs)<n>We propose POP, a self-play framework that uses the same LLM to synthesize evaluation rubrics, along with input-output pairs, for each example.<n>On Qwen-2.5-7B, POP increases performance of both pretrained and instruction-tuned models, across different tasks.
• Score: 14.278605706996474
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Self-play has recently emerged as a promising paradigm to train Large Language Models (LLMs). In self-play, the target LLM creates the task input (e.g., ask a question), which it then addresses itself by producing a task output (e.g., give an answer). A reward model evaluates the output, and the rewards are then used to train the LLM, typically via Reinforcement Learning (RL). Self-play incurs minimal supervision costs, and this is especially helpful for post-training LLMs, which require high-quality input-output pairs that traditionally have to be written by humans or expensive proprietary models. However, existing work explores self-play only for verifiable tasks such as math and coding. Instead, we seek to extend it to more realistic open-ended tasks. In particular, we propose POP, a self-play framework that uses the same LLM to synthesize evaluation rubrics, along with input-output pairs, for each example. The rubric is then used to evaluate outputs and train the model. We further ground the framework on a content-rich pretraining corpus to (1) ensure a generation-verification gap and reduce reward hacking, and (2) prevent mode collapse. On Qwen-2.5-7B, POP increases performance of both pretrained and instruction-tuned models, across different tasks ranging from long-form Healthcare QA to creative writing and instruction following.

Related papers

• LLM2Vec-Gen: Generative Embeddings from Large Language Models [38.742293185880364]
  We propose a novel self-supervised approach to training embedding models.<n>Rather than encoding the input, we learn to represent the model's potential response.<n>We observe up to 43.2% reduction in harmful content retrieval and 29.3% improvement in reasoning capabilities for embedding tasks.
  arXiv  Detail & Related papers  (2026-03-11T15:58:47Z)
• Incentivizing LLMs to Self-Verify Their Answers [22.387551134333084]
  We propose a framework that incentivizes Large Language Models to self-verify their own answers.<n>We train our self-verification models based on Qwen2.5-Math-7B and DeepSeek-R1-Distill-Qwen-1.5B.<n> Experiments on multiple mathematical reasoning benchmarks show that our models can not only improve post-training performance but also enable effective test-time scaling.
  arXiv  Detail & Related papers  (2025-06-02T06:54:29Z)
• Language Models can Self-Lengthen to Generate Long Texts [74.96074422345806]
  This paper introduces an innovative iterative training framework called Self-Lengthen. It leverages only the intrinsic knowledge and skills of Large Language Models without the need for auxiliary data or proprietary models. Experiments on benchmarks and human evaluations show that Self-Lengthen outperforms existing methods in long-text generation.
  arXiv  Detail & Related papers  (2024-10-31T13:47:10Z)
• Online Intrinsic Rewards for Decision Making Agents from Large Language Model Feedback [52.763620660061115]
  ONI is a distributed architecture that simultaneously learns an RL policy and an intrinsic reward function.<n>We explore a range of algorithmic choices for reward modeling with varying complexity.<n>Our approach achieves state-of-the-art performance across a range of challenging tasks from the NetHack Learning Environment.
  arXiv  Detail & Related papers  (2024-10-30T13:52:43Z)
• SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning [70.21358720599821]
  Large language models (LLMs) hold the promise of solving diverse tasks when provided with appropriate natural language prompts. We propose SELF-GUIDE, a multi-stage mechanism in which we synthesize task-specific input-output pairs from the student LLM. We report an absolute improvement of approximately 15% for classification tasks and 18% for generation tasks in the benchmark's metrics.
  arXiv  Detail & Related papers  (2024-07-16T04:41:58Z)
• ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search [50.45155830888697]
  We develop a reinforced self-training approach, called ReST-MCTS*, based on integrating process reward guidance with tree search MCTS* for collecting higher-quality reasoning traces as well as per-step value to train policy and reward models. We first show that the tree-search policy in ReST-MCTS* achieves higher accuracy compared with prior LLM reasoning baselines such as Best-of-N and Tree-of-Thought, within the same search budget.
  arXiv  Detail & Related papers  (2024-06-06T07:40:00Z)
• Get my drift? Catching LLM Task Drift with Activation Deltas [55.75645403965326]
  Task drift allows attackers to exfiltrate data or influence the LLM's output for other users.<n>We show that a simple linear classifier can detect drift with near-perfect ROC AUC on an out-of-distribution test set.<n>We observe that this approach generalizes surprisingly well to unseen task domains, such as prompt injections, jailbreaks, and malicious instructions.
  arXiv  Detail & Related papers  (2024-06-02T16:53:21Z)
• RL-VLM-F: Reinforcement Learning from Vision Language Foundation Model Feedback [24.759613248409167]
  Reward engineering has long been a challenge in Reinforcement Learning research. We propose RL-VLM-F, a method that automatically generates reward functions for agents to learn new tasks. We demonstrate that RL-VLM-F successfully produces effective rewards and policies across various domains.
  arXiv  Detail & Related papers  (2024-02-06T04:06:06Z)
• LLM-Pruner: On the Structural Pruning of Large Language Models [65.02607075556742]
  Large language models (LLMs) have shown remarkable capabilities in language understanding and generation. We tackle the compression of LLMs within the bound of two constraints: being task-agnostic and minimizing the reliance on the original training dataset. Our method, named LLM-Pruner, adopts structural pruning that selectively removes non-critical coupled structures.
  arXiv  Detail & Related papers  (2023-05-19T12:10:53Z)
• Generation-driven Contrastive Self-training for Zero-shot Text Classification with Instruction-following LLM [31.25193238045053]
  We introduce a novel method, namely GenCo, which leverages the strong generative power of large language models to assist in training a smaller language model. In our method, an LLM plays an important role in the self-training loop of a smaller model in two important ways. It helps crafting additional high-quality training pairs, by rewriting input texts conditioned on predicted labels.
  arXiv  Detail & Related papers  (2023-04-24T07:35:38Z)
• Automating Code-Related Tasks Through Transformers: The Impact of Pre-training [15.129062963782005]
  We study the impact of pre-training objectives on the performance of transformers when automating code-related tasks. We pre-train 32 transformers using both (i) generic pre-training objectives usually adopted in software engineering (SE) literature; and (ii) pre-training objectives tailored to specific code-related tasks.
  arXiv  Detail & Related papers  (2023-02-08T13:37:33Z)
• Attributed Question Answering: Evaluation and Modeling for Attributed Large Language Models [68.37431984231338]
  Large language models (LLMs) have shown impressive results across a variety of tasks while requiring little or no direct supervision. We believe the ability of an LLM to an attribute to the text that it generates is likely to be crucial for both system developers and users in this setting.
  arXiv  Detail & Related papers  (2022-12-15T18:45:29Z)

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.