Discriminative Finetuning of Generative Large Language Models without Reward Models and Human Preference Data

• URL: http://arxiv.org/abs/2502.18679v2
• Date: Mon, 12 May 2025 22:10:13 GMT
• Title: Discriminative Finetuning of Generative Large Language Models without Reward Models and Human Preference Data
• Authors: Siqi Guo, Ilgee Hong, Vicente Balmaseda, Changlong Yu, Liang Qiu, Xin Liu, Haoming Jiang, Tuo Zhao, Tianbao Yang,
• Abstract summary: Supervised fine-tuning (SFT) has become a crucial step for aligning pretrained large language models (LLMs)<n>We introduce Discriminative Fine-Tuning (DFT), an improved variant of SFT, which mitigates the burden of collecting human-labeled preference data.<n>Our contributions include: (i) a discriminative probabilistic framework for fine-tuning LLMs by explicitly modeling the discriminative likelihood of an answer among all possible outputs given an input; (ii) efficient algorithms to optimize this discriminative likelihood; and (iii) extensive experiments demonstrating DFT's effectiveness
• Score: 73.04828796123581
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Supervised fine-tuning (SFT) has become a crucial step for aligning pretrained large language models (LLMs) using supervised datasets of input-output pairs. However, despite being supervised, SFT is inherently limited by its generative training objective. To address its limitations, the existing common strategy is to follow SFT with a separate phase of preference optimization (PO), which relies on either human-labeled preference data or a strong reward model to guide the learning process. In this paper, we address the limitations of SFT by exploring one of the most successful techniques in conventional supervised learning: discriminative learning. We introduce Discriminative Fine-Tuning (DFT), an improved variant of SFT, which mitigates the burden of collecting human-labeled preference data or training strong reward models. Unlike SFT that employs a generative approach and overlooks negative data, DFT adopts a discriminative paradigm that increases the probability of positive answers while suppressing potentially negative ones, aiming for data prediction instead of token prediction. Our contributions include: (i) a discriminative probabilistic framework for fine-tuning LLMs by explicitly modeling the discriminative likelihood of an answer among all possible outputs given an input; (ii) efficient algorithms to optimize this discriminative likelihood; and (iii) extensive experiments demonstrating DFT's effectiveness, achieving performance better than SFT and comparable to if not better than SFT$\rightarrow$PO. The code can be found at https://github.com/Optimization-AI/DFT.

Related papers

• On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification [50.30835290642069]
  We present a simple yet theoretically motivated improvement to Supervised Fine-Tuning (SFT) for the Large Language Model (LLM)<n>We reveal that standard SFT gradients implicitly encode a problematic reward structure that may severely restrict the generalization capabilities of model.<n>We propose Dynamic Fine-Tuning (DFT), stabilizing gradient updates for each token by dynamically rescaling the objective function with the probability of this token.
  arXiv  Detail & Related papers  (2025-08-07T17:59:04Z)
• Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections [65.36449542323277]
  We present a unified theoretical framework bridgingSupervised Fine-Tuning (SFT) and preference learning in Large Language Model (LLM) post-training.<n>We propose a simple yet effective learning rate reduction approach that yields significant performance improvements.
  arXiv  Detail & Related papers  (2025-06-15T05:42:29Z)
• ActiveDPO: Active Direct Preference Optimization for Sample-Efficient Alignment [94.36403843133616]
  Using human preferences to align large language models (LLMs) has significantly improved their performance in various downstream tasks.<n>Existing methods either lack a strong theoretical foundation or depend on restrictive reward function assumptions.<n>We propose an algorithm, ActiveDPO, that uses a theoretically grounded data selection criterion for non-linear reward functions.
  arXiv  Detail & Related papers  (2025-05-25T17:42:52Z)
• UFT: Unifying Supervised and Reinforcement Fine-Tuning [21.195897792629548]
  We propose Unified Fine-Tuning (UFT), a novel post-training paradigm that unifies SFT and RFT into a single, integrated process.<n>UFT enables the model to effectively explore solutions while incorporating informative supervision signals.<n>We theoretically prove that UFT breaks RFT's inherent exponential sample complexity bottleneck.
  arXiv  Detail & Related papers  (2025-05-22T17:53:57Z)
• 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.<n>The intuition is to boost SFT by imposing a particular preference: textitfavoring the target model over aligned LLMs on the same SFT data.<n>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)
• SPRec: Self-Play to Debias LLM-based Recommendation [23.875509546540904]
  Large language models (LLMs) have attracted significant attention in recommendation systems.<n>We propose SPRec, a novel self-play framework designed to mitigate over-recommendation and improve fairness without requiring additional data or manual intervention.
  arXiv  Detail & Related papers  (2024-12-12T12:53:30Z)
• UFT: Unifying Fine-Tuning of SFT and RLHF/DPO/UNA through a Generalized Implicit Reward Function [18.54945183526789]
  We introduce Unified Fine-Tuning (UFT), which integrates SFT and alignment into a single training stage.<n>Our experimental results demonstrate that UFT outperforms SFT on instruction-tuning data alone.<n>When combining instruction-tuning data with alignment data, UFT effectively prevents catastrophic forgetting.
  arXiv  Detail & Related papers  (2024-10-28T18:34:25Z)
• Data Selection via Optimal Control for Language Models [134.67665351539725]
  This work investigates the selection of high-quality pre-training data from massive corpora to enhance LMs' capabilities for downstream usage. We introduce PMP-based Data Selection (PDS), a framework that approximates optimal data selection by solving the PMP conditions. The benefits of PDS extend to 400B models trained on 10T tokens, as evidenced by the extrapolation of the test loss curves according to the Scaling Laws.
  arXiv  Detail & Related papers  (2024-10-09T17:06:57Z)
• ASFT: Aligned Supervised Fine-Tuning through Absolute Likelihood [14.512464277772194]
  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.
  arXiv  Detail & Related papers  (2024-09-14T11:39:13Z)
• Geometric-Averaged Preference Optimization for Soft Preference Labels [78.2746007085333]
  Many algorithms for aligning LLMs with human preferences assume that human preferences are binary and deterministic.<n>In this work, we introduce the distributional soft preference labels and improve Direct Preference Optimization (DPO) with a weighted geometric average of the LLM output likelihood in the loss function.
  arXiv  Detail & Related papers  (2024-09-10T17:54:28Z)
• Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT for LLM Alignment [65.15914284008973]
  We propose to leverage an Inverse Reinforcement Learning (IRL) technique to simultaneously build an reward model and a policy model. We show that the proposed algorithms converge to the stationary solutions of the IRL problem. Our results indicate that it is beneficial to leverage reward learning throughout the entire alignment process.
  arXiv  Detail & Related papers  (2024-05-28T07:11:05Z)
• 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.<n>To mitigate overoptimization, we first propose a theoretical algorithm that chooses the best policy for an adversarially chosen reward model.<n>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)
• Intuitive Fine-Tuning: Towards Simplifying Alignment into a Single Process [26.196705232699884]
  We introduce Intuitive Fine-Tuning (IFT) to integrate SFT and Preference Optimization into a single process. IFT performs comparably or even superiorly to sequential recipes of SFT and some typical Preference Optimization methods. An explainable Frozen Lake game further validates the effectiveness of IFT for getting competitive policy.
  arXiv  Detail & Related papers  (2024-05-20T08:23:28Z)
• Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data [102.16105233826917]
  Learning from preference labels plays a crucial role in fine-tuning large language models. There are several distinct approaches for preference fine-tuning, including supervised learning, on-policy reinforcement learning (RL), and contrastive learning.
  arXiv  Detail & Related papers  (2024-04-22T17:20:18Z)
• Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive [15.066029556877721]
  We show theoretically that the standard DPO loss can lead to a reduction of the model's likelihood of the preferred examples. We design DPO-Positive (DPOP), a new loss function and training procedure which avoids this failure mode. Surprisingly, we find that DPOP outperforms DPO and other fine-tuning procedures across a wide variety of datasets and downstream tasks.
  arXiv  Detail & Related papers  (2024-02-20T18:42:34Z)
• Functional Graphical Models: Structure Enables Offline Data-Driven Optimization [111.28605744661638]
  We show how structure can enable sample-efficient data-driven optimization. We also present a data-driven optimization algorithm that infers the FGM structure itself.
  arXiv  Detail & Related papers  (2024-01-08T22:33:14Z)

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.