IRDS: Interpretable RLVR Data Selection via Verifier-Coupled Sparse Autoencoder Coverage

• URL: http://arxiv.org/abs/2605.28247v1
• Date: Wed, 27 May 2026 09:58:05 GMT
• Title: IRDS: Interpretable RLVR Data Selection via Verifier-Coupled Sparse Autoencoder Coverage
• Abstract summary: We present IRDS (Inter- pretable RLVR Data Selection), which selects RLVR training instances on a sparse autoen- coder (SAE) cluster basis.<n>Experiments on three instruction- tuned models and six math reasoning bench- marks show that IRDS achieves the highest overall accuracy.
• Score: 12.520216206687044
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a key technique for en- hancing LLM reasoning, yet its data ineffi- ciency remains a major bottleneck. Existing methods address this problem only partially, each missing at least one of subset-level cov- erage, verifier signal use, or interpretability. To address this gap, we present IRDS (Inter- pretable RLVR Data Selection), which selects RLVR training instances on a sparse autoen- coder (SAE) cluster basis so the selection itself is auditable on recognizable problem motifs. To select instances the model both fails on and can still learn from, we introduce a verifier- coupled coverage objective on the SAE basis and solve it by greedy log-determinant max- imization. Experiments on three instruction- tuned models and six math reasoning bench- marks show that IRDS achieves the highest overall accuracy, exceeding the strongest base- line by +3.9/+4.0 pp on the two Qwen models and by +0.5 pp on Llama-3.1-8B, while run- ning an order of magnitude cheaper than the trajectory-based baseline.

Related papers

• CircuitLens: Reasoning Circuits as Data Selection Signals for Reinforcement Learning with Verifiable Rewards [9.41727721095383]
  Circuit Reasoning Score (CRS) is a selection signal derived from 46 reasoning-sensitive attention heads.<n>CRS runs against the intuitive hypothesis that stronger reasoning-circuit engagement produces better training data.
  arXiv  Detail & Related papers  (2026-09-07T08:14:26Z)
• Architecture-Dependent Causal Transfer of Activation States Across Large Language Models [51.56484100374058]
  Internal language activation states can be transferred causally between different large language models.<n>Injecting projected activations into a target model during generation produces a statistically significant, preregistered causal effect.<n>We conclude that end-to-end activation-state transfer between LLMs, as currently implemented, is architecture-dependent rather than universal.
  arXiv  Detail & Related papers  (2026-08-17T09:53:27Z)
• When RLVR Shrinks the Reasoning Boundary: Diagnosing Pass@k Inversion [0.0]
  Reinforcement learning with verifiable rewards (RLVR) can improve one-sample accuracy while making a model worse under repeated sampling.<n>We study this pass@k inversion: after training, the policy may solve fewer distinct problems than its base model at large $k$.<n>The failure concentrates on boundary prompts, where the base model contains rare correct trajectories that are recoverable by sampling but too sparse to reliably appear in finite RLVR rollout groups.
  arXiv  Detail & Related papers  (2026-07-12T17:17:18Z)
• Reinforcement Learning with Robust Rubric Rewards [30.826907231502663]
  We propose Reinforcement Learning with Robust Rewards ($textRLR3$), extending RLVR from task-level verification to criterion-level verification.<n>$textRLR3$ routes instance-specific rubrics through two execution paths: an LLM-as-an-extractor paired with a deterministic verifier, or an LLM-as-a-Judge for non-verifiable criteria.<n>$textRLR3$ consistently outperforms RLVR, yielding a 4.7-point improvement over the base model and exceeding the official instruct-to-thinking model gap.
  arXiv  Detail & Related papers  (2026-05-28T17:11:03Z)
• Self-Verified Distillation: Your Language Model Is Secretly Its Own Synthetic Data Pipeline [56.53954182896384]
  We propose Self-Verified Distillation, a simple post-training refinement algorithm for large language models.<n>Self-Verified Distillation generates candidate solutions to unlabeled seed questions.<n>It filters them using prompt-based self-verification, and trains on the resulting self-curated dataset.<n>We find that sampling more candidate generations and using a larger verification budget during training data construction produces higher-quality self-curated data.
  arXiv  Detail & Related papers  (2026-05-20T17:26:10Z)
• Learn More with Less: Uncertainty Consistency Guided Query Selection for RLVR [18.494852448006462]
  Existing RLVR algorithms require large query budgets, making annotation costly.<n>We investigate whether fewer but more informative queries can yield similar or superior performance, introducing active learning (AL) into RLVR.<n>Experiments show our method consistently outperforms random and classic AL baselines, achieving full-dataset performance while training on only 30% of the data.
  arXiv  Detail & Related papers  (2026-01-30T05:41:55Z)
• Every Question Has Its Own Value: Reinforcement Learning with Explicit Human Values [53.72318444646282]
  We propose Reinforcement Learning with Explicit Human Values (RLEV)<n>RLEV aligns Large Language Model (LLM) optimization directly with quantifiable human value signals.<n>We show RLEV consistently outperforms correctness-only baselines across multiple RL algorithms and model scales.
  arXiv  Detail & Related papers  (2025-10-23T04:15:22Z)
• LaSeR: Reinforcement Learning with Last-Token Self-Rewarding [54.72617309922891]
  Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a core paradigm for enhancing the reasoning capabilities of Large Language Models (LLMs)<n>Previous practice requires the LLM to sequentially generate solutions and self-verifications using two separate prompt templates, which significantly reduces efficiency.<n>We propose LaSeR (Reinforcement Learning with Last-Token Self-Rewarding), an algorithm that simply augments the original RLVR loss with a MSE loss.
  arXiv  Detail & Related papers  (2025-10-16T17:55:11Z)
• QiMeng-CodeV-R1: Reasoning-Enhanced Verilog Generation [51.393569044134445]
  Large language models (LLMs) trained via reinforcement learning with verifiable reward (RLVR) have achieved breakthroughs on tasks with explicit, automatable verification.<n> Extending RLVR to automatically generating hardware description languages (HDLs) like Verilog from natural-language (NL) specifications, however, poses three key challenges.<n>We introduce CodeV-R1, an RLVR framework for training Verilog generation LLMs.
  arXiv  Detail & Related papers  (2025-05-30T03:51:06Z)
• KECOR: Kernel Coding Rate Maximization for Active 3D Object Detection [48.66703222700795]
  We resort to a novel kernel strategy to identify the most informative point clouds to acquire labels. To accommodate both one-stage (i.e., SECOND) and two-stage detectors, we incorporate the classification entropy tangent and well trade-off between detection performance and the total number of bounding boxes selected for annotation. Our results show that approximately 44% box-level annotation costs and 26% computational time are reduced compared to the state-of-the-art method.
  arXiv  Detail & Related papers  (2023-07-16T04:27:03Z)

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.