Towards Bridging the Reward-Generation Gap in Direct Alignment Algorithms (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks, including instruction following, mathematical problem solving, and coding generation. |
| Approach: | They propose a method that truncates both preferred and dispreferred responses to match the shorter one’s length. |
| Outcome: | The proposed approach improves over standard implementations and achieves 11.8 points in AlpacaEval 2 and overall improvements across downstream tasks. |
Similar Papers
Reward Alignment Optimization: A Direct Point-wise Alignment Approach (2026.acl-long)
Copied to clipboard
| Challenge: | Existing Direct Alignment Algorithms (DAAs) are limiting in generalizaiton to implicit rewards. |
| Approach: | They propose a point-wise direct alignment method that uses an explicit reward model to specify exact target generation probabilities and align the policy offline towards them. |
| Outcome: | The proposed method outperforms existing direct alignment algorithms while enabling controllable target probability distributions. |
AlignDistil: Token-Level Language Model Alignment as Adaptive Policy Distillation (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for LLM alignment optimize tokens using a sparse, response-level reward or preference annotation. |
| Approach: | They propose an RLHF-equivalent distillation method for token-level reward optimization that incorporates the reward learned by DPO into the RLHG objective and builds a token-based teacher distribution. |
| Outcome: | The proposed method bridges the accuracy gap between the reward from the DPO model and the pure reward model by building a contrastive DPO reward with a normal and a reverse DPO. |
Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization (2024.findings-acl)
Copied to clipboard
| Challenge: | Recent approaches to language model alignment assume homogeneous human preferences, but actual human preferences vary widely and are hard to satisfy with a single language model. |
| Approach: | They propose an RL-free extension of Direct Preference Optimization (DPO) that folds language modeling directly into reward modeling and trains language models as collective reward models that combine all objectives with specific weights. |
| Outcome: | The proposed method matches or outperforms existing methods in safety alignment and long-form question answering. |
What Do LLMs Learn First? Asymmetric Learning Dynamics of Input Complexity and Output Ambiguity in Preference Alignment (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods treat all preference pairs uniformly during training. |
| Approach: | They propose a training framework that maintains separate, adaptive pacing schedules for each dimension. |
| Outcome: | The proposed training framework outperforms curriculum baselines by 2.1% and 0.21 points . it achieves 42.3% length-controlled win rate on AlpacaEval 2.0 and 7.66 on MT-Bench . |
Beyond Online Sampling: Bridging Offline-to-Online Alignment via Dynamic Data Transformation for LLMs (2025.emnlp-main)
Copied to clipboard
| Challenge: | Direct Preference Optimization (DPO) eliminates complex reward modeling in aligning large language models with human preferences, but its online variant faces significant efficiency bottlenecks due to costly real-time preference sampling and the reward model annotation. |
| Approach: | They propose a framework that transforms static datasets into dynamically adaptive equivalents without the need for an explicit reward model. |
| Outcome: | The proposed approach matches or exceeds the performance of a fully online DPO. |
Dynamic Rewarding with Prompt Optimization Enables Tuning-free Self-Alignment of Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Empirical evaluations on eight recent LLMs reveal that DRPO significantly enhances alignment performance, enabling base models to outperform their SFT/RLHF-tuned counterparts. |
| Approach: | They propose a tuning-free approach to self-alignment called Dynamic Rewarding with Prompt Optimization (DRPO) it leverages a dynamic rewarding mechanism to identify and rectify alignment weaknesses . |
| Outcome: | The proposed approach outperforms existing methods and is highly adaptable to various alignment challenges. |
Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies attributed verbosity to biased labels, but new research shows that DPO can be effective in mitigating verboses. |
| Approach: | They propose to use a method to reduce the amount of verbosity in LLMs by using a downsampling approach. |
| Outcome: | The proposed approach overcomes the problem of verbosity by reducing the length reliance of the proposed algorithm. |
RS-DPO: A Hybrid Rejection Sampling and Direct Preference Optimization Method for Alignment of Large Language Models (2024.findings-naacl)
Copied to clipboard
| Challenge: | Reinforcement learning with human feedback (RLHF) is widely employed to align large language models with user intent. |
| Approach: | They propose to combine rejection sampling and direct preference optimization to improve alignment with user intent by identifying pairs of contrastive samples from human annotator and alternative LLMs. |
| Outcome: | The proposed method outperforms existing methods including RS, PPO, and DPO in a limited resource environment. |
CRPO: Confidence-Reward Driven Preference Optimization for Machine Translation (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have shown great potential in natural language processing tasks, but their application to machine translation remains challenging due to pretraining on predominantly English-centric datasets. |
| Approach: | They propose a method that combines reward scores with model confidence to improve model selection for fine-tuning. |
| Outcome: | The proposed method outperforms existing methods in translation accuracy and data efficiency. |
Sem-DPO: Mitigating Semantic Inconsistency in Preference Optimization for Prompt Engineering (2026.findings-acl)
Copied to clipboard
Anas Mohamed, Azal Ahmad Khan, Xinran Wang, Ahmad Faraz Khan, Shuwen Ge, Saman Bahzad Khan, Ayaan Ahmad, Ali Anwar
| Challenge: | Direct Preference Optimization (DPO) is an off-policy alternative to RL for automatic prompt engineering, but its token-level regularization leaves semantic inconsistency unchecked as prompts that win higher preference scores can still drift away from the user’s intended meaning. |
| Approach: | They propose a variant of Direct Preference Optimization that preserves semantic consistency while maintaining its simplicity and efficiency. |
| Outcome: | The proposed model outperforms state-of-the-art prompt optimization baselines and several DPO variants on three standard text-to-image prompt-optimization benchmarks and three language models. |