ASFT: Aligned Supervised Fine-Tuning through Absolute Likelihood
- URL: http://arxiv.org/abs/2409.10571v1
- Date: Sat, 14 Sep 2024 11:39:13 GMT
- Title: ASFT: Aligned Supervised Fine-Tuning through Absolute Likelihood
- Authors: Ruoyu Wang, Jiachen Sun, Shaowei Hua, Quan Fang,
- Abstract summary: Aligned Supervised Fine-Tuning (ASFT) is an effective approach that better aligns Large Language Models with pair-wise datasets.
ASFT mitigates the issue where the DPO loss function decreases the probability of generating human-dispreferred data.
Extensive experiments demonstrate that ASFT is an effective alignment approach, consistently outperforming existing methods.
- Score: 14.512464277772194
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Direct Preference Optimization (DPO) is a method for enhancing model performance by directly optimizing for the preferences or rankings of outcomes, instead of traditional loss functions. This approach has proven effective in aligning Large Language Models (LLMs) with human preferences. Despite its widespread use across various tasks, DPO has been criticized for its sensitivity to the effectiveness of Supervised Fine-Tuning (SFT) and its limitations in enabling models to learn human-preferred responses, leading to less satisfactory performance. To address these limitations, we propose Aligned Supervised Fine-Tuning (ASFT), an effective approach that better aligns LLMs with pair-wise datasets by optimizing absolute likelihood for each response, rather than using the Bradley-Terry model, and eliminates the need for a reference model. Through theoretical gradient analysis, we demonstrate that ASFT mitigates the issue where the DPO loss function decreases the probability of generating human-dispreferred data at a faster rate than it increases the probability of producing preferred data. Additionally, we compare ASFT to DPO and its latest variants, such as the single-step approach ORPO, using the latest instruction-tuned model Llama3, which has been fine-tuned on UltraFeedback and HH-RLHF. We evaluated performance on instruction-following benchmarks like MT-Bench and traditional text generation metrics such as BLEU-4 and ROUGE-L. Extensive experiments demonstrate that ASFT is an effective alignment approach, consistently outperforming existing methods.
Related papers
- Length-Controlled Margin-Based Preference Optimization without Reference Model [11.878496378814045]
We propose Length-Controlled Margin-Based Preference Optimization (LMPO) for preference-based reinforcement learning.
A key innovation of LMPO lies in its Length-Controlled Margin-Based loss function, integrated within the Bradley-Terry framework.
Our experimental results demonstrate that LMPO effectively controls response length, reduces probability degradation, and outperforms existing approaches.
arXiv Detail & Related papers (2025-02-20T15:30:27Z) - Dynamic Noise Preference Optimization for LLM Self-Improvement via Synthetic Data [51.62162460809116]
We introduce Dynamic Noise Preference Optimization (DNPO) to ensure consistent improvements across iterations.
In experiments with Zephyr-7B, DNPO consistently outperforms existing methods, showing an average performance boost of 2.6%.
DNPO shows a significant improvement in model-generated data quality, with a 29.4% win-loss rate gap compared to the baseline in GPT-4 evaluations.
arXiv Detail & Related papers (2025-02-08T01:20:09Z) - Preference-Oriented Supervised Fine-Tuning: Favoring Target Model Over Aligned Large Language Models [12.500777267361102]
We introduce a novel textbfpreference-textbforiented supervised textbffine-textbftuning approach, namely PoFT.
The intuition is to boost SFT by imposing a particular preference: textitfavoring the target model over aligned LLMs on the same SFT data.
PoFT achieves stable and consistent improvements over the SFT baselines across different training datasets and base models.
arXiv Detail & Related papers (2024-12-17T12:49:14Z) - Direct Preference Optimization Using Sparse Feature-Level Constraints [47.15096507230884]
Feature-level constrained Preference Optimization is a novel method designed to simplify the alignment process while ensuring stability.
Our approach enjoys efficiency by using sparse features activated in a well-trained sparse autoencoder and the quality of sequential KL divergence.
arXiv Detail & Related papers (2024-11-12T07:54:13Z) - Reward-Augmented Data Enhances Direct Preference Alignment of LLMs [63.32585910975191]
We introduce reward-conditioned Large Language Models (LLMs) that learn from the entire spectrum of response quality within the dataset.
We propose an effective yet simple data relabeling method that conditions the preference pairs on quality scores to construct a reward-augmented dataset.
arXiv Detail & Related papers (2024-10-10T16:01:51Z) - Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization [75.1240295759264]
We propose an effective framework for Bridging and Modeling Correlations in pairwise data, named BMC.
We increase the consistency and informativeness of the pairwise preference signals through targeted modifications.
We identify that DPO alone is insufficient to model these correlations and capture nuanced variations.
arXiv Detail & Related papers (2024-08-14T11:29:47Z) - Self-Augmented Preference Optimization: Off-Policy Paradigms for Language Model Alignment [104.18002641195442]
We introduce Self-Augmented Preference Optimization (SAPO), an effective and scalable training paradigm that does not require existing paired data.
Building on the self-play concept, which autonomously generates negative responses, we further incorporate an off-policy learning pipeline to enhance data exploration and exploitation.
arXiv Detail & Related papers (2024-05-31T14:21:04Z) - Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer [52.09480867526656]
We identify the source of misalignment as a form of distributional shift and uncertainty in learning human preferences.
To mitigate overoptimization, we first propose a theoretical algorithm that chooses the best policy for an adversarially chosen reward model.
Using the equivalence between reward models and the corresponding optimal policy, the algorithm features a simple objective that combines a preference optimization loss and a supervised learning loss.
arXiv Detail & Related papers (2024-05-26T05:38:50Z) - Multi-Reference Preference Optimization for Large Language Models [56.84730239046117]
We introduce a novel closed-form formulation for direct preference optimization using multiple reference models.
The resulting algorithm, Multi-Reference Preference Optimization (MRPO), leverages broader prior knowledge from diverse reference models.
Our experiments demonstrate that LLMs finetuned with MRPO generalize better in various preference data, regardless of data scarcity or abundance.
arXiv Detail & Related papers (2024-05-26T00:29:04Z) - Statistical Rejection Sampling Improves Preference Optimization [42.57245965632205]
We introduce a novel approach to source preference data from the target optimal policy using rejection sampling.
We also propose a unified framework that enhances the loss functions used in both Sequence Likelihood (SLiC) and Direct Preference Optimization (DPO) from a preference modeling standpoint.
arXiv Detail & Related papers (2023-09-13T01:07:25Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.