HyperDPO: Hypernetwork-based Multi-Objective Fine-Tuning Framework

• URL: http://arxiv.org/abs/2410.08316v1
• Date: Thu, 10 Oct 2024 19:06:39 GMT
• Title: HyperDPO: Hypernetwork-based Multi-Objective Fine-Tuning Framework
• Authors: Yinuo Ren, Tesi Xiao, Michael Shavlovsky, Lexing Ying, Holakou Rahmanian,
• Abstract summary: HyperDPO is a hypernetwork-based approach that extends the Direct Preference Optimization (DPO) technique. By substituting the Bradley-Terry-Luce model in DPO with the Plackett-Luce model, our framework is capable of handling a wide range of MOFT tasks.
• Score: 11.342075103251576
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In LLM alignment and many other ML applications, one often faces the Multi-Objective Fine-Tuning (MOFT) problem, i.e. fine-tuning an existing model with datasets labeled w.r.t. different objectives simultaneously. To address the challenge, we propose the HyperDPO framework, a hypernetwork-based approach that extends the Direct Preference Optimization (DPO) technique, originally developed for efficient LLM alignment with preference data, to accommodate the MOFT settings. By substituting the Bradley-Terry-Luce model in DPO with the Plackett-Luce model, our framework is capable of handling a wide range of MOFT tasks that involve listwise ranking datasets. Compared with previous approaches, HyperDPO enjoys an efficient one-shot training process for profiling the Pareto front of auxiliary objectives, and offers flexible post-training control over trade-offs. Additionally, we propose a novel Hyper Prompt Tuning design, that conveys continuous weight across objectives to transformer-based models without altering their architecture. We demonstrate the effectiveness and efficiency of the HyperDPO framework through its applications to various tasks, including Learning-to-Rank (LTR) and LLM alignment, highlighting its viability for large-scale ML deployments.

Related papers

• Robust Multi-Objective Preference Alignment with Online DPO [6.434799451791957]
  Multi-objective preference alignment is critical for developing AI systems that are personalizable, helpful, and safe. Existing approaches are either computationally expensive to train or do not sufficiently steer model behaviors. This paper introduces the Multi-Objective Online DPO algorithm, designed to robustly and efficiently align model behaviors with multiple, potentially conflicting human preferences.
  arXiv  Detail & Related papers  (2025-03-01T02:01:49Z)
• CHiP: Cross-modal Hierarchical Direct Preference Optimization for Multimodal LLMs [107.21334626890713]
  Multimodal Large Language Models (MLLMs) still struggle with hallucinations despite their impressive capabilities. We propose a Cross-modal Hierarchical Direct Preference Optimization (CHiP) to address these limitations. We evaluate CHiP through both quantitative and qualitative analyses, with results across multiple benchmarks demonstrating its effectiveness in reducing hallucinations.
  arXiv  Detail & Related papers  (2025-01-28T02:05:38Z)
• Few-shot Steerable Alignment: Adapting Rewards and LLM Policies with Neural Processes [50.544186914115045]
  Large language models (LLMs) are increasingly embedded in everyday applications. Ensuring their alignment with the diverse preferences of individual users has become a critical challenge. We present a novel framework for few-shot steerable alignment.
  arXiv  Detail & Related papers  (2024-12-18T16:14:59Z)
• Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs [76.40876036912537]
  Large Language Models (LLMs) demonstrate strong few-shot adaptability without requiring fine-tuning. Current Visual Foundation Models (VFMs) require explicit fine-tuning with sufficient tuning data. We propose a framework, LoRA Recycle, that distills a meta-LoRA from diverse pre-tuned LoRAs with a meta-learning objective.
  arXiv  Detail & Related papers  (2024-12-03T07:25:30Z)
• Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization [65.64108848398696]
  We introduce a preference optimization process to enhance the multimodal reasoning capabilities of MLLMs. We develop a simple yet effective method, termed Mixed Preference Optimization (MPO), which boosts multimodal CoT performance. Our model, InternVL2-8B-MPO, achieves an accuracy of 67.0 on MathVista, outperforming InternVL2-8B by 8.7 points and achieving performance comparable to the 10x larger InternVL2-76B.
  arXiv  Detail & Related papers  (2024-11-15T18:59:27Z)
• Align$^2$LLaVA: Cascaded Human and Large Language Model Preference Alignment for Multi-modal Instruction Curation [56.75665429851673]
  This paper introduces a novel instruction curation algorithm, derived from two unique perspectives, human and LLM preference alignment. Experiments demonstrate that we can maintain or even improve model performance by compressing synthetic multimodal instructions by up to 90%.
  arXiv  Detail & Related papers  (2024-09-27T08:20:59Z)
• NVLM: Open Frontier-Class Multimodal LLMs [64.00053046838225]
  We introduce NVLM 1.0, a family of frontier-class multimodal large language models (LLMs) that achieve state-of-the-art results on vision-language tasks. We propose a novel architecture that enhances both training efficiency and multimodal reasoning capabilities. We develop production-grade multimodality for the NVLM-1.0 models, enabling them to excel in vision-language tasks.
  arXiv  Detail & Related papers  (2024-09-17T17:59:06Z)
• The Ultimate Guide to Fine-Tuning LLMs from Basics to Breakthroughs: An Exhaustive Review of Technologies, Research, Best Practices, Applied Research Challenges and Opportunities [0.35998666903987897]
  This report examines the fine-tuning of Large Language Models (LLMs) It outlines the historical evolution of LLMs from traditional Natural Language Processing (NLP) models to their pivotal role in AI. The report introduces a structured seven-stage pipeline for fine-tuning LLMs.
  arXiv  Detail & Related papers  (2024-08-23T14:48:02Z)
• Understanding Alignment in Multimodal LLMs: A Comprehensive Study [46.33812471516309]
  We analyze each aspect of preference alignment in Multimodal Large Language Models (MLLMs) We show that combining offline and online methods can improve the performance of the model in certain scenarios. We introduce a novel way of creating multimodal preference data called Bias-Driven Hallucination Sampling (BDHS)
  arXiv  Detail & Related papers  (2024-07-02T17:55:03Z)
• Teola: Towards End-to-End Optimization of LLM-based Applications [13.478509565946354]
  Large language model (LLM)-based applications contribute to the end-to-end latency. Existing frameworks employ coarse-grained orchestration with task modules, which confines optimizations to within each module. We propose fine-grained end-to-end orchestration, which utilizes task primitives as the basic units and represents each query's workflow as a primitive-level dataflow graph.
  arXiv  Detail & Related papers  (2024-06-29T05:59:53Z)
• 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)
• 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)
• CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion [58.15403987979496]
  CREMA is a generalizable, highly efficient, and modular modality-fusion framework for video reasoning. We propose a novel progressive multimodal fusion design supported by a lightweight fusion module and modality-sequential training strategy. We validate our method on 7 video-language reasoning tasks assisted by diverse modalities, including VideoQA and Video-Audio/3D/Touch/Thermal QA.
  arXiv  Detail & Related papers  (2024-02-08T18:27:22Z)
• Using Large Language Models for Hyperparameter Optimization [29.395931874196805]
  This paper explores the use of foundational large language models (LLMs) in hyper parameter optimization (HPO) Our empirical evaluations on standard benchmarks reveal that within constrained search budgets, LLMs can match or outperform traditional HPO methods.
  arXiv  Detail & Related papers  (2023-12-07T18:46:50Z)
• Self-Evolutionary Optimization for Pareto Front Learning [34.17125297176668]
  Multi-objective optimization (MOO) approaches have been proposed for multitasking problems. Recent MOO methods approximate multiple optimal solutions (Pareto front) with a single unified model. We show that PFL can be re-formulated into another MOO problem with multiple objectives, each of which corresponds to different preference weights for the tasks.
  arXiv  Detail & Related papers  (2021-10-07T13:38:57Z)

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.