Papers with sampling distribution
COPR: Continual Human Preference Learning via Optimal Policy Regularization (2025.findings-acl)
Copied to clipboard
Han Zhang, Lin Gui, Yu Lei, Yuanzhao Zhai, Yehong Zhang, Zhuo Zhang, Yulan He, Hui Wang, Yue Yu, Kam-Fai Wong, Bin Liang, Ruifeng Xu
| Challenge: | Reinforcement Learning from Human Feedback (RLHF) is effective for aligning Large Language Models with human preferences, but its complex process limits its ability to continually learn human feedback. |
| Approach: | They propose a non-RL offline method to convert historical optimal policies into optimization constraints when continually learning new preferences. |
| Outcome: | The proposed method outperforms strong CL baselines in terms of reward-based evaluations and human assessment. |
Target Conditioned Sampling: Optimizing Data Selection for Multilingual Neural Machine Translation (P19-1)
Copied to clipboard
| Challenge: | Existing studies show that training on a single related language is more effective than using all data. |
| Approach: | They propose an efficient algorithm that first samples a target sentence, and then conditionally samples its source sentence. |
| Outcome: | The proposed algorithm brings significant gains on three of four languages with minimal training overhead. |
Revisiting Self-Consistency from Dynamic Distributional Alignment Perspective on Answer Aggregation (2025.findings-acl)
Copied to clipboard
Yiwei Li, Ji Zhang, Shaoxiong Feng, Peiwen Yuan, Xinglin Wang, Jiayi Shi, Yueqi Zhang, Chuyi Tan, Boyuan Pan, Yao Hu, Kan Li
| Challenge: | Existing studies on self-consistency show that it improves reasoning abilities by aggregating diverse stochastic samples. |
| Approach: | They propose a confidence-driven mechanism that dynamically calibrates temperature to align with high probability modes. |
| Outcome: | The proposed method outperforms fixed-diversity baselines on reasoning tasks and improves both average and best-case performance. |
DynamixSFT: Dynamic Mixture Optimization of Instruction Tuning Collections (2026.findings-acl)
Copied to clipboard
| Challenge: | Several studies rely on additional models to optimize mixtures. |
| Approach: | They propose a method that dynamically optimizes instruction-tuning dataset mixtures by prior-scaled Boltzmann Exploration and a multi-armed bandit setup. |
| Outcome: | The proposed method improves the TÜLU-2-mixture and TÜLO-3-mixtures across 10 benchmarks while introducing minimal computational overhead over naive sampling. |