When Implausible Tokens Get Reinforced: Tail-Aware Credit Calibration for LLM Reinforcement Learning
arXiv:2607.07976v1 Announce Type: new Abstract: Reinforcement learning (RL) has achieved remarkable success in enhancing the reasoning capabilities of large language models (LLMs). However, widely…
Read the full articleYou might also wanna read
ConSPO: A Contrastive Approach to Improving Reinforcement Learning with Verifiable Rewards for LLMs
Group Relative Policy Optimization (GRPO) is one of the most widely adopted RLVR algorithms for post-training large language models on reaso
arxiv.org·1mo ago
LK Losses: A New Training Objective to Optimize Acceptance Rate in Speculative Decoding for LLMs
Speculative decoding accelerates autoregressive large language model (LLM) inference by using a lightweight draft model to propose candidate
arxiv.org·1mo ago
New Framework Formalizes Learning from Language Feedback with Provable Performance Guarantees
Interactively learning from observation and language feedback is an increasingly studied area driven by the emergence of large language mode
arxiv.org·29d ago
Contextual Rollout Bandits: A Neural Scheduling Framework for Efficient Reinforcement Learning with Verifiable Rewards
Reinforcement Learning with Verifiable Rewards (RLVR) is an effective paradigm for improving the reasoning capabilities of large language mo
arxiv.org·1mo ago
Ouro: Looped Language Models That Build Reasoning into Pre-Training Through Latent Space Iteration
Modern LLMs are trained to "think" primarily via explicit text generation, such as chain-of-thought (CoT), which defers reasoning to post-tr
arxiv.org·6mo ago
RICP: A Teacher-Student Framework for Retrieved In-Context Principles from Mistakes in LLMs
In-context learning (ICL) has been instrumental in adapting Large Language Models (LLMs) to downstream tasks using correct input-output exam
arxiv.org·1mo ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.