Challenge: Experimental results show that the methods enhanced by DEFT outperform the original methods in both alignment capability and generalization ability, with significantly reduced training time.
Approach: They propose a distribution-based alignment framework that integrates data filtering and distributional guidance to improve alignment efficiency and generalization ability.
Outcome: The proposed framework outperforms existing methods in alignment capability and generalization ability with significantly reduced training time.

Similar Papers

Reinforcement Learning with Supervised Alignment (2025.findings-emnlp)

Copied to clipboard

Challenge: Supervised fine-tuning (SFT) is a widely used method for adapting Large Language Models to specific tasks.
Approach: They propose a method that uses supervised fine-tuning to train a reward model for reinforcement learning.
Outcome: The proposed method outperforms existing methods on in-domain benchmarks but surpasses them 50 times on out-of-domain and cross-task evaluations.
Back to Basics: Revisiting REINFORCE-Style Optimization for Learning from Human Feedback in LLMs (2024.acl-long)

Copied to clipboard

Challenge: Proximal Policy Optimization (PPO) is used for RLHF but requires high computational cost and sensitive hyperparameter tuning.
Approach: They propose to use Proximal Policy Optimization to align large language models to human preferences.
Outcome: The proposed method preserves and even increases performance while preserving the motivational principles that led to the development of PPO.
SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF (2023.findings-emnlp)

Copied to clipboard

Challenge: supervised fine-tuning and reinforcement learning from human feedback (RLHF) are not effective in generating useful and high-quality responses.
Approach: They propose a supervised fine-tuning method that empowers end-users to control responses during inference.
Outcome: Experiments show that supervised fine-tuning and reinforcement learning from human feedback (RLHF) can generate helpful and high-quality responses while maintaining customizability.
CLHA: A Simple Yet Effective Contrastive Learning Framework for Human Alignment (2024.lrec-main)

Copied to clipboard

Challenge: Large language models (LLMs) have attracted considerable attention from academic and industrial communities due to their outstanding performance in various natural language processing tasks.
Approach: They propose a Contrastive Learning Framework for Human Alignment to evaluate the noise within the data and dynamically adjust the training process.
Outcome: The proposed framework surpasses other algorithms in terms of reward model scores, automatic evaluations, and human assessments on the widely used dataset "Helpful and Harmless"
Don’t Forget Your Reward Values: Language Model Alignment via Value-based Calibration (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods for generating large language models have been criticized for their complexity and instability.
Approach: They propose a value-based calibration method to better align Large Language Models with human preferences.
Outcome: The proposed method surpasses existing methods on AI assistant and summarization datasets, providing impressive generalizability, robustness, and diversity in different settings.
Gradient-Adaptive Policy Optimization: Towards Multi-Objective Alignment of Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Reinforcement learning from human feedback (RLHF) has emerged as a powerful technique for aligning large language models (LLMs) with human preferences.
Approach: They propose a novel algorithm that uses multiple-gradient descent to optimize LLMs with diverse preferences to maximize trade-offs between objectives.
Outcome: The proposed approach incorporates user preferences across different objectives and achieves Pareto solutions that better align with the user’s specific needs.
Bridging SFT and RL: Dynamic Policy Optimization for Robust Reasoning (2026.findings-acl)

Copied to clipboard

Challenge: Existing unified optimization strategies overlook the statistical conflict between these distinct gradient signals.
Approach: They propose a framework to reduce bias-variance trade-offs in Large Language Models . they propose DYPO, which leverages intrinsic group dynamics to significantly reduce RL gradient variance .
Outcome: The proposed framework outperforms traditional pipelines on reasoning benchmarks and out-of-distribution tasks.
Compatibility-Aware Dynamic Fine-Tuning for Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: Recent work attributes optimization instability to the low probability of demonstrations being incompatible with the sample level.
Approach: They propose a Dynamic Fine-Tuning extension of DFT that controls sample-level optimization variance.
Outcome: The proposed model can generalize token-level stabilization to the sample level while remaining fully supervised and free of reward modeling.
A Deep Dive into the Trade-Offs of Parameter-Efficient Preference Alignment Techniques (2024.acl-long)

Copied to clipboard

Challenge: Large language models are pre-trained on trillions of tokens and instruction-tuned or aligned to specific preferences.
Approach: They propose guidelines to help researchers perform more effective parameter-efficient LLM alignment.
Outcome: The proposed methods outperform preference optimization and outperformed pre-trained models on three key axes.
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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations