REVIEW 12 cited by
One-shot Entropy Minimization
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
We trained 13,440 large language models and found that entropy minimization requires only a single unlabeled data and 10 steps optimization to achieve performance improvements comparable to or even greater than those obtained using thousands of data and carefully designed rewards in rule-based reinforcement learning. This striking result may prompt a rethinking of post-training paradigms for large language models. Our code is avaliable at https://github.com/zitian-gao/one-shot-em.
Forward citations
Cited by 12 Pith papers
-
Rethinking Entropy Minimization in Test-Time Adaptation for Autoregressive Models
Derives a rigorous entropy minimization formulation for autoregressive test-time adaptation that decomposes into policy gradient and entropy terms, reinterpreting prior methods and improving Whisper ASR across 20+ domains.
-
SELF-EMO: Emotional Self-Evolution from Recognition to Consistent Expression
SELF-EMO lets LLMs bootstrap better emotion recognition and expression via self-play, data flywheel filtering with smoothed IoU rewards, and SELF-GRPO reinforcement learning, yielding SOTA gains on IEMOCAP, MELD, and ...
-
Relationship-Centered Care: Relatedness and Responsible Design for Human Connections in Mental-Health Care
Length-aware GFlowNet matching of α-power base distributions elicits either stronger LLM reasoning (α>1) or restored creativity (α<1) without external supervision, matching or beating RLIF and GRPO baselines.
-
What are Key Factors for Updates in RL for LLM Reasoning?
Theoretical analysis of RLVR update dynamics leads to ACPO, an adaptive clipping method that outperforms DAPO and CISPO on reasoning benchmarks with 3B and 7B models.
-
Experience Sharing in Mutual Reinforcement Learning for Heterogeneous Language Models
Mutual Reinforcement Learning allows heterogeneous LLMs to exchange experience through mechanisms like Peer Rollout Pooling, Cross-Policy GRPO Advantage Sharing, and Success-Gated Transfer, with outcome-level sharing ...
-
TEMPO: Scaling Test-time Training for Large Reasoning Models
TEMPO scales test-time training for large reasoning models by interleaving policy refinement on unlabeled data with critic recalibration on labeled data via an EM formulation, yielding large gains on AIME tasks.
-
HEALing Entropy Collapse: Enhancing Exploration in Few-Shot RLVR via Hybrid-Domain Entropy Dynamics Alignment
HEAL mitigates entropy collapse in few-shot RLVR by selectively adding general-domain data and aligning trajectory-level entropy dynamics, matching full-shot performance with 32 target samples.
-
Compute as Teacher: Turning Inference Compute Into Reference-Free Supervision
Parallel inference rollouts aggregated into pseudo-references enable reference-free RL supervision that matches expert-annotated performance on health tasks while using 9x less test-time compute.
-
Know When to Explore: Difficulty-Aware Certainty as a Guide for LLM Reinforcement Learning
A new RL reward-shaping method that rewards low confidence on hard problems and high confidence on easy ones improves LLM math reasoning over a GRPO baseline.
-
Trust Region On-Policy Distillation
TrOPD stabilizes on-policy distillation for LLMs with trust-region learning, outlier estimation, and off-policy guidance, outperforming prior OPD methods on reasoning and code benchmarks.
-
Token-Level Policy Optimization: Linking Group-Level Rewards to Token-Level Aggregation via Sequence-Level Likelihood
TEPO uses sequence-level likelihood for token-level reward aggregation and a KL mask on positive-advantage tokens to improve stability and performance over GRPO in mathematical reasoning.
-
Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents
EMPG re-weights policy-gradient updates by step-level token entropy, amplifying confident correct actions and muting uncertain ones, and adds a future-clarity bonus.
Discussion (0). Sign in to comment.