# Insights into Alignment: Evaluating DPO and its Variants Across Multiple Tasks

arXiv: https://arxiv.org/abs/2404.14723 · HTML: https://mlsanity.com/paper/2404.14723/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- Placed in LLM preference optimization methods, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 32 of its 46 references that are in the map.
- First posted on arXiv 23 Apr 2024.

## Placed in

- LLM alignment / RLHF / preference optimisation / [LLM preference optimization methods](https://mlsanity.com/alignment/llm-preference-optimization-methods/)

## Builds on (most cited first, 30 of 32)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions](https://mlsanity.com/paper/1905.10044/) (2019)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [Solving Quantitative Reasoning Problems with Language Models](https://mlsanity.com/paper/2206.14858/) (2022)
- [A General Theoretical Paradigm to Understand Learning from Human Preferences](https://mlsanity.com/paper/2310.12036/) (2023)
- [Enhancing Chat Language Models by Scaling High-quality Instructional Conversations](https://mlsanity.com/paper/2305.14233/) (2023)
- [AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback](https://mlsanity.com/paper/2305.14387/) (2023)
- [Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models](https://mlsanity.com/paper/2401.01335/) (2024)
- [Zephyr: Direct Distillation of LM Alignment](https://mlsanity.com/paper/2310.16944/) (2023)
- [Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation](https://mlsanity.com/paper/2401.08417/) (2024)

## Built on by (most cited first, 30 of 35)

- [Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback](https://mlsanity.com/paper/2406.09279/) (2024)
- [RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold](https://mlsanity.com/paper/2406.14532/) (2024)
- [Reinforcement Learning Enhanced LLMs: A Survey](https://mlsanity.com/paper/2412.10400/) (2024)
- [A Survey of Direct Preference Optimization](https://mlsanity.com/paper/2503.11701/) (2025)
- [Fine-tuning Large Language Models for Improving Factuality in Legal Question Answering](https://mlsanity.com/paper/2501.06521/) (2025)
- [A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applications](https://mlsanity.com/paper/2410.15595/) (2024)
- [BPO: Towards Balanced Preference Optimization between Knowledge Breadth and Depth in Alignment](https://mlsanity.com/paper/2411.10914/) (2024)
- [RainbowPO: A Unified Framework for Combining Improvements in Preference Optimization](https://mlsanity.com/paper/2410.04203/) (2024)
- [Towards a Unified View of Preference Learning for Large Language Models: A Survey](https://mlsanity.com/paper/2409.02795/) (2024)
- [PRefLexOR: Preference-based Recursive Language Modeling for Exploratory Optimization of Reasoning and Agentic Thinking](https://mlsanity.com/paper/2410.12375/) (2024)
- [Triple Preference Optimization: Achieving Better Alignment using a Single Step Optimization](https://mlsanity.com/paper/2405.16681/) (2024)
- [PORT: Preference Optimization on Reasoning Traces](https://mlsanity.com/paper/2406.16061/) (2024)
- [Fine Tuning Large Language Models for Medicine: The Role and Importance of Direct Preference Optimization](https://mlsanity.com/paper/2409.12741/) (2024)
- [As Simple as Fine-tuning: LLM Alignment via Bidirectional Negative Feedback Loss](https://mlsanity.com/paper/2410.04834/) (2024)
- [Gradient Imbalance in Direct Preference Optimization](https://mlsanity.com/paper/2502.20847/) (2025)
- [TODO: Enhancing LLM Alignment with Ternary Preferences](https://mlsanity.com/paper/2411.02442/) (2024)
- [The Root Shapes the Fruit: On the Persistence of Gender-Exclusive Harms in Aligned Language Models](https://mlsanity.com/paper/2411.03700/) (2024)
- [Understanding the Logic of Direct Preference Alignment through Logic](https://mlsanity.com/paper/2412.17696/) (2024)
- [Entropy-Based Adaptive Weighting for Self-Training](https://mlsanity.com/paper/2503.23913/) (2025)
- [Balancing the Budget: Understanding Trade-offs Between Supervised and Preference-Based Finetuning](https://mlsanity.com/paper/2502.11284/) (2025)
- [Efficient Safety Retrofitting Against Jailbreaking for LLMs](https://mlsanity.com/paper/2502.13603/) (2025)
- [The Alignment Tax: Response Homogenization in Aligned LLMs and Its Implications for Uncertainty Estimation](https://mlsanity.com/paper/2603.24124/) (2026)
- [The Differences Between Direct Alignment Algorithms are a Blur](https://mlsanity.com/paper/2502.01237/) (2025)
- [Improving LLM Safety and Helpfulness using SFT and DPO: A Study on OPT-350M](https://mlsanity.com/paper/2509.09055/) (2025)
- [Knowledge Graph-Assisted LLM Post-Training for Enhanced Legal Reasoning](https://mlsanity.com/paper/2601.13806/) (2026)
- [Mesh-Pro: Asynchronous Advantage-guided Ranking Preference Optimization for Artist-style Quadrilateral Mesh Generation](https://mlsanity.com/paper/2603.00526/) (2026)
- [Improved Algorithms for Differentially Private Language Model Alignment](https://mlsanity.com/paper/2505.08849/) (2025)
- [What Is Preference Optimization Doing, and Why?](https://mlsanity.com/paper/2512.00778/) (2025)
- [Federated Personal Knowledge Graph Completion with Lightweight Large Language Models for Personalized Recommendations](https://mlsanity.com/paper/2603.13264/) (2026)
- [Do Post-Training Algorithms Actually Differ? A Controlled Study Across Model Scales Uncovers Scale-Dependent Ranking Inversions](https://mlsanity.com/paper/2603.19335/) (2026)

## Abstract (arXiv)

This study evaluates Direct Preference Optimization (DPO) and its variants for aligning Large Language Models (LLMs) with human preferences, testing three configurations: (1) with Supervised Fine Tuning (SFT), (2) without SFT, and (3) without SFT but using an instruction tuned model. We further investigate how training set size influences model performance. Our evaluation spans 13 benchmarks covering dialogue, reasoning, mathematical problem-solving, question answering, truthfulness, MT-Bench, Big Bench, and the Open LLM Leaderboard. We find that: (1) alignment methods often achieve near optimal performance even with smaller subsets of training data; (2) although they offer limited improvements on complex reasoning tasks, they enhance mathematical problem-solving; and (3) using an instruction tuned model improves truthfulness. These insights highlight the conditions under which alignment methods excel, as well as their limitations.