skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Align-Pro: A Principled Approach to Prompt Optimization for LLM Alignment
The alignment of large language models (LLMs) with human values is critical as these models become increasingly integrated into various societal and decision-making processes. Traditional methods, such as reinforcement learning from human feedback (RLHF), achieve alignment by fine-tuning model parameters, but these approaches are often computationally expensive and impractical when models are frozen or inaccessible for parameter modification. In contrast, prompt optimization is a viable alternative to RLHF for LLM alignment. While the existing literature has shown empirical promise of prompt optimization, its theoretical underpinning remains under-explored. We address this gap by formulating prompt optimization as an optimization problem and try to provide theoretical insights into the optimality of such a framework. To analyze the performance of the prompt optimization, we study theoretical suboptimality bounds and provide insights in terms of how prompt optimization depends upon the given prompter and target model. We also provide empirical validation through experiments on various datasets, demonstrating that prompt optimization can effectively align LLMs, even when parameter fine-tuning is not feasible.  more » « less
Award ID(s):
2106339
PAR ID:
10591590
Author(s) / Creator(s):
; ; ; ; ;
Publisher / Repository:
AAAI
Date Published:
Journal Name:
Proceedings of the AAAI Conference on Artificial Intelligence
Volume:
39
Issue:
26
ISSN:
2159-5399
Page Range / eLocation ID:
27653 to 27661
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; (, 38th Conference on Neural Information Processing Systems (NeurIPS 2024))
    Large language models (LLMs) are trained on a deluge of text data with limited quality control. As a result, LLMs can exhibit unintended or even harmful behaviours, such as leaking information, fake news or hate speech. Countermeasures, commonly referred to as preference alignment, include fine-tuning the pretrained LLMs with carefully crafted text examples of desired behaviour. Even then, empirical evidence shows preference aligned LLMs can be enticed to harmful behaviour. This so called jailbreaking of LLMs is typically achieved by adversarially modifying the input prompt to the LLM. Our paper provides theoretical insights into the phenomenon of preference alignment and jailbreaking from a statistical perspective. Under our framework, we first show that pretrained LLMs will mimic harmful behaviour if present in the training corpus. Under that same framework, we then introduce a statistical notion of alignment, and lower-bound the jailbreaking probability, showing that it is unpreventable under reasonable assumptions. Based on our insights, we propose an alteration to the currently prevalent alignment strategy RLHF. Specifically, we introduce a simple modification to the RLHF objective, we call E-RLHF, that aims to increase the likelihood of safe responses. E-RLHF brings no additional training cost, and is compatible with other methods. Empirically, we demonstrate that E-RLHF outperforms RLHF on all alignment problems put forward by the AdvBench and HarmBench project without sacrificing model performance as measured by the MT-Bench project. 
    more » « less
  2. ; ; ; ; (, Proceedings of Machine Learning Research)
    Reinforcement Learning from Human Feedback (RLHF) has shown promise in aligning large language models (LLMs). Yet its reliance on a singular reward model often overlooks the diversity of human preferences. Recent approaches address this limitation by leveraging multi-dimensional feedback to fine-tune corresponding reward models and train LLMs using reinforcement learning. However, the process is costly and unstable, especially given the competing and heterogeneous nature of human preferences. In this paper, we propose Mixing Preference Optimization (MPO), a post-processing framework for aggregating single-objective policies as an alternative to both multi-objective RLHF (MORLHF) and MaxMin-RLHF. MPO avoids alignment from scratch. Instead, it log-linearly combines existing policies into a unified one with the weight of each policy computed via a batch stochastic mirror descent. Empirical results demonstrate that MPO achieves balanced performance across diverse preferences, outperforming or matching existing models with significantly reduced computational costs. 
    more » « less
  3. ; ; (, International Conference on Learning Representations (ICLR 2025))
    Diffusion-based Text-to-Image (T2I) models have achieved impressive success in generating high-quality images from textual prompts. While large language models (LLMs) effectively leverage Direct Preference Optimization (DPO) for fine-tuning on human preference data without the need for reward models, diffusion models have not been extensively explored in this area. Current preference learning methods applied to T2I diffusion models immediately adapt existing techniques from LLMs. However, this direct adaptation introduces an estimated loss specific to T2I diffusion models. This estimation can potentially lead to suboptimal performance through our empirical results. In this work, we propose Direct Score Preference Optimization (DSPO), a novel algorithm that aligns the pretraining and fine-tuning objectives of diffusion models by leveraging score matching, the same objective used during pretraining. It introduces a new perspective on preference learning for diffusion models. Specifically, DSPO distills the score function of human-preferred image distributions into pretrained diffusion models, fine-tuning the model to generate outputs that align with human preferences. We theoretically show that DSPO shares the same optimization direction as reinforcement learning algorithms in diffusion models under certain conditions. Our experimental results demonstrate that DSPO outperforms preference learning baselines for T2I diffusion models in human preference evaluation tasks and enhances both visual appeal and prompt alignment of generated images. 
    more » « less
  4. ; ; (, International Conference on Machine Learning 2024)
    Large language models (LLMs) are trained on a deluge of text data with limited quality control. As a result, LLMs can exhibit unintended or even harmful behaviours, such as leaking information, fake news or hate speech. Countermeasures, commonly referred to as preference alignment, include fine-tuning the pretrained LLMs with carefully crafted text examples of desired behaviour. Even then, empirical evidence shows preference aligned LLMs can be enticed to harmful behaviour. This so called jailbreaking of LLMs is typically achieved by adversarially modifying the input prompt to the LLM. Our paper provides theoretical insights into the phenomenon of preference alignment and jailbreaking from a statistical perspective. Under our framework, we first show that pretrained LLMs will mimic harmful behaviour if present in the training corpus. \textbf{Under that same framework, we then introduce a statistical notion of alignment, and lower-bound the jailbreaking probability, showing that it is unpreventable under reasonable assumptions.} 
    more » « less
  5. (, University of Washington)
    High-quality instruction data is critical for aligning large language models (LLMs). Although some models, such as Llama-3-Instruct, have open weights, their alignment data remain private, which hinders the democratization of AI. High human labor costs and a limited, predefined scope for prompting prevent existing open-source data creation methods from scaling effectively, potentially limiting the diversity and quality of public alignment datasets. Is it possible to synthesize high-quality instruction data at scale by extracting it directly from an aligned LLM? We present a self-synthesis method for generating large-scale alignment data named Magpie. Our key observation is that aligned LLMs like Llama-3-Instruct can generate a user query when we input only the pre-query templates up to the position reserved for user messages, thanks to their auto-regressive nature. We use this method to prompt Llama-3-Instruct and generate 4 million instructions along with their corresponding responses. We further introduce extensions of Magpie for filtering, generating multi-turn, preference optimization, domain-specific and multilingual datasets. We perform a comprehensive analysis of the Magpie-generated data. To compare Magpie-generated data with other public instruction datasets (eg, ShareGPT, WildChat, Evol-Instruct, Ultra-Chat, OpenHermes, Tulu-V2-Mix, GenQA), we fine-tune Llama-3-8B-Base with each dataset and evaluate the performance of the fine-tuned models. Our results indicate that using Magpie for supervised fine-tuning (SFT) solely can surpass the performance of previous public datasets utilized for both SFT and preference optimization, such as direct preference optimization with UltraFeedback. We also show that in some tasks, models supervised fine-tuned with Magpie perform comparably to the official Llama-3-8B-Instruct, despite the latter being enhanced with 10 million data points through SFT and subsequent preference optimization. This advantage is evident on alignment benchmarks such as AlpacaEval, ArenaHard, and WildBench. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Text Encoded Conversion
  • XML
  • Save / Share this Record
  • Send to Email