The Flow has not summarised this story yet — read it at arXiv Computation and Language.
arXiv:2606. 29639v1 Announce Type: cross Abstract: Automatic prompt optimization is still underexplored for episodic few-shot relation extraction with smaller language models.
The paper introduces RECAP, a redundancy-aware credit assignment method that improves reasoning efficiency in large language models by assigning credit to each reasoning step based on its downstream role and contribution to the correct answer. RECAP uses a semantic dependency graph to measure structural responsibility and evaluates step efficacy via changes in gold-answer log-likelihood, enabling step-specific updates without requiring a separate reward model or concise trajectories. Experiments on two 7B models across four mathematical reasoning benchmarks show that RECAP enhances the accuracy-efficiency trade-off, boosting pass@1 by 2.0–3.7 percentage points while cutting reasoning tokens by 8–31% compared to GRPO.
arXiv:2506.13502v4 Announce Type: replace Abstract: Next-word prediction (NWP) trains language models against a single observed continuation, even though many contexts admit multiple plausible next w...
arXiv:2510. 11194v3 Announce Type: replace Abstract: Personalized alignment is crucial for enabling Large Language Models (LLMs) to engage effectively in user-centric interactions.
Post-training of reasoning language models is commonly driven by supervised distillation and reinforcement learning with verifiable rewards. Distillation often relies on chain-of-thought annotations that are expensive to obtain and may themselves be noisy, incomplete, or partially incorrect; even when the final solution is correct, an imperfect rationale can interfere with learning.
arXiv:2606. 19327v1 Announce Type: new Abstract: Post-training of reasoning language models is commonly driven by supervised distillation and reinforcement learning with verifiable rewards.