From Credit Assignment to Entropy Regularization: Two New Algorithms for Neural Sequence Prediction (P18-1)
Copied to clipboard
| Challenge: | equivalence between credit assignment problem and entropy regularized reinforcement learning is established . a wide range of successful sequence prediction algorithms have been developed . |
| Approach: | They propose to extend credit assignment in reward augmented maximum likelihood learning by credit assignment and entropy regularization. |
| Outcome: | The proposed algorithms outperform RAML and Actor-Critic on two benchmark datasets. |
Similar Papers
T-REG: Preference Optimization with Token-Level Reward Regularization (2025.acl-long)
Copied to clipboard
| Challenge: | Reinforcement learning from human feedback (RLHF) is a dominant approach for large language models to follow instructions and produce meaningful alignment. |
| Approach: | They propose a method that leverages human feedback to optimize large language models . they propose to use sequence-level and token-level rewards to optimize preference . |
| Outcome: | The proposed method outperforms baseline methods on Alpaca Eval 2 and Arena-Hard benchmarks. |
Learning to Rank Generation with Pairwise Partial Rewards (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for conditional text generation suffer from large action space and delayed reward, as the reward can be computed only after an entire sequence is generated. |
| Approach: | They propose a method that provides partial rewards for intermediate actions taken on partial sequences to prioritize actions that lead to the generation of more desirable sequences. |
| Outcome: | The proposed method overcomes the limitations of the prevalent supervised maximum likelihood estimation approach. |
Exploring Supervised and Unsupervised Rewards in Machine Translation (2021.eacl-main)
Copied to clipboard
| Challenge: | Autoregressive sequence-to-sequence (seq2sequ) neural architectures have become the de facto approach in Machine Translation (MT). |
| Approach: | They propose to make models less reliant on cross-entropy loss and evaluation metrics . they propose an entropicity-regularised RL method that explores the action space . |
| Outcome: | The proposed method exploits the action space and unsupervised reward function to balance between exploration and exploitation. |
Entropy-Aware Reshaping of Reinforcement Signals for Multi-Answer Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Reinforcement learning with verifiable rewards (RLVR) is a standard post-training paradigm for large language models. |
| Approach: | They propose a framework that reshapes how learning signals are normalized and aggregated. |
| Outcome: | Experiments on MCTACO and MMLU-Multi show that the proposed framework improves accuracy, training stability and cross-dataset transfer performance. |
Inverse Reinforcement Learning Meets Large Language Model Alignment (2025.acl-tutorials)
Copied to clipboard
| Challenge: | This tutorial will provide a comprehensive review of recent advances in LLM alignment . it will highlight the necessity of constructing neural reward models from human data . |
| Approach: | This tutorial will provide a comprehensive review of recent advances in LLM alignment through the lens of inverse reinforcement learning. |
| Outcome: | This tutorial will provide a comprehensive review of recent advances in LLM alignment through the lens of inverse reinforcement learning (IRL). |
Revisiting Entropy Regularization: Adaptive Coefficient Unlocks Its Potential for LLM Reinforcement Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Reasoning ability is a defining capability of Large Language Models (LLMs), but RLVR training suffers from policy entropy collapse, hindering exploration and limiting reasoning performance. |
| Approach: | They propose a framework that dynamically balances exploration and exploitation via three components: difficulty-aware coefficient allocation, initial-anchored target entropy, and dynamic global coefficient adjustment. |
| Outcome: | The proposed framework outperforms baselines on multiple mathematical reasoning benchmarks. |
Exploiting Tree Structure for Credit Assignment in Reinforcement Learning with Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Reinforcement learning has shown strong promise for strengthening reasoning ability of large language models, but sparse, delayed rewards make token-level credit assignment a central challenge. |
| Approach: | They propose a critic-free algorithm that rewards tokens that change the solution. |
| Outcome: | The proposed algorithm improves on in-distribution benchmarks and out-of-disttribution settings. |
Re3val: Reinforced and Reranked Generative Retrieval (2024.findings-eacl)
Copied to clipboard
| Challenge: | generative retrieval models encode pointers to information in a corpus as an index within the model’s parameters. |
| Approach: | They propose a generative retrieval model that leverages contextual information to rerank retrieved page titles and utilizes REINFORCE to maximize rewards generated by constrained decoding. |
| Outcome: | The proposed model can't be tuned for the downstream readers as decoding the page title is a non-differentiable operation. |
Breaking Consensus Bias: Unsupervised Reinforcement Learning for Machine Translation (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing RL approaches for MT face fixed references or the production of homogeneous references leading to mode collapse in unsupervised settings. |
| Approach: | They propose an Entropy-Driven Unsupervised RL framework for machine translation that leverages entropy for supervision construction and self-evolution. |
| Outcome: | The proposed framework outperforms supervised and unsupervised baselines in multiple language pairs. |
Orchestrating Tokens and Sequences: Dynamic Hybrid Policy Optimization for RLVR (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing RLVR algorithms focus on different granularities and have complementary strengths and limitations. |
| Approach: | They propose a framework for reinforcement learning with verifiable rewards that bridges RLVR and GSPO . group-level importance ratios are used to update a policy, which preserves fine-grained credit assignment . |
| Outcome: | The proposed framework outperforms existing methods on seven reasoning benchmarks. |