Token-level Proximal Policy Optimization for Query Generation

• URL: http://arxiv.org/abs/2411.00722v1
• Date: Fri, 01 Nov 2024 16:36:14 GMT
• Title: Token-level Proximal Policy Optimization for Query Generation
• Authors: Yichen Ouyang, Lu Wang, Fangkai Yang, Pu Zhao, Chenghua Huang, Jianfeng Liu, Bochen Pang, Yaming Yang, Yuefeng Zhan, Hao Sun, Qingwei Lin, Saravan Rajmohan, Weiwei Deng, Dongmei Zhang, Feng Sun, Qi Zhang,
• Abstract summary: State-of-the-art query generation methods leverage Large Language Models (LLMs) for their strong capabilities in context understanding and text generation. We propose Token-level Proximal Policy Optimization (TPPO), a noval approach designed to empower LLMs perform better in query generation through fine-tuning. TPPO is based on the Reinforcement Learning from AI Feedback (RLAIF) paradigm, consisting of a token-level reward model and a token-level proximal policy optimization module.
• Score: 45.81132350185301
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Query generation is a critical task for web search engines (e.g. Google, Bing) and recommendation systems. Recently, state-of-the-art query generation methods leverage Large Language Models (LLMs) for their strong capabilities in context understanding and text generation. However, they still face challenges in generating high-quality queries in terms of inferring user intent based on their web search interaction history. In this paper, we propose Token-level Proximal Policy Optimization (TPPO), a noval approach designed to empower LLMs perform better in query generation through fine-tuning. TPPO is based on the Reinforcement Learning from AI Feedback (RLAIF) paradigm, consisting of a token-level reward model and a token-level proximal policy optimization module to address the sparse reward challenge in traditional RLAIF frameworks. To evaluate the effectiveness and robustness of TPPO, we conducted experiments on both open-source dataset and an industrial dataset that was collected from a globally-used search engine. The experimental results demonstrate that TPPO significantly improves the performance of query generation for LLMs and outperforms its existing competitors.

Related papers

• LREF: A Novel LLM-based Relevance Framework for E-commerce [14.217396055372053]
  This paper proposes a novel framework called the LLM-based RElevance Framework (LREF) aimed at enhancing e-commerce search relevance. We evaluate the performance of the framework through a series of offline experiments on large-scale real-world datasets, as well as online A/B testing. The model was deployed in a well-known e-commerce application, yielding substantial commercial benefits.
  arXiv  Detail & Related papers  (2025-03-12T10:10:30Z)
• A Survey of Direct Preference Optimization [103.59317151002693]
  Large Language Models (LLMs) have demonstrated unprecedented generative capabilities. Their alignment with human values remains critical for ensuring helpful and harmless deployments. Direct Preference Optimization (DPO) has recently gained prominence as a streamlined alternative.
  arXiv  Detail & Related papers  (2025-03-12T08:45:15Z)
• LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning [56.273799410256075]
  The framework combines Monte Carlo Tree Search (MCTS) with iterative Self-Refine to optimize the reasoning path. The framework has been tested on general and advanced benchmarks, showing superior performance in terms of search efficiency and problem-solving capability.
  arXiv  Detail & Related papers  (2024-10-03T18:12:29Z)
• VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment [66.80143024475635]
  We propose VinePPO, a straightforward approach to compute unbiased Monte Carlo-based estimates. We show that VinePPO consistently outperforms PPO and other RL-free baselines across MATH and GSM8K datasets.
  arXiv  Detail & Related papers  (2024-10-02T15:49:30Z)
• GenCRF: Generative Clustering and Reformulation Framework for Enhanced Intent-Driven Information Retrieval [20.807374287510623]
  We propose GenCRF: a Generative Clustering and Reformulation Framework to capture diverse intentions adaptively. We show that GenCRF achieves state-of-the-art performance, surpassing previous query reformulation SOTAs by up to 12% on nDCG@10.
  arXiv  Detail & Related papers  (2024-09-17T05:59:32Z)
• Towards Boosting LLMs-driven Relevance Modeling with Progressive Retrieved Behavior-augmented Prompting [23.61061000692023]
  This study proposes leveraging user interactions recorded in search logs to yield insights into users' implicit search intentions. We propose ProRBP, a novel Progressive Retrieved Behavior-augmented Prompting framework for integrating search scenario-oriented knowledge with Large Language Models.
  arXiv  Detail & Related papers  (2024-08-18T11:07:38Z)
• ACE: A Generative Cross-Modal Retrieval Framework with Coarse-To-Fine Semantic Modeling [53.97609687516371]
  We propose a pioneering generAtive Cross-modal rEtrieval framework (ACE) for end-to-end cross-modal retrieval. ACE achieves state-of-the-art performance in cross-modal retrieval and outperforms the strong baselines on Recall@1 by 15.27% on average.
  arXiv  Detail & Related papers  (2024-06-25T12:47:04Z)
• Self-Exploring Language Models: Active Preference Elicitation for Online Alignment [88.56809269990625]
  We propose a bilevel objective optimistically biased towards potentially high-reward responses to actively explore out-of-distribution regions. Our experimental results demonstrate that when fine-tuned on Zephyr-7B-SFT and Llama-3-8B-Instruct models, Self-Exploring Language Models (SELM) significantly boosts the performance on instruction-following benchmarks.
  arXiv  Detail & Related papers  (2024-05-29T17:59:07Z)
• DPO Meets PPO: Reinforced Token Optimization for RLHF [36.97894955691627]
  We introduce a framework that models RLHF problems as a Markov decision process (MDP) Under this framework, we introduce an algorithm, dubbed as Reinforced Token Optimization (textttRTO), which learns the token-wise reward function from preference data. For its practical implementation, textttRTO innovatively integrates Direct Preference Optimization (DPO) and Proximal Policy Optimization.
  arXiv  Detail & Related papers  (2024-04-29T17:58:30Z)
• Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement [67.1393112206885]
  Large Language Models (LLMs) have shown promise as intelligent agents in interactive decision-making tasks. We introduce Entropy-Regularized Token-level Policy Optimization (ETPO), an entropy-augmented RL method tailored for optimizing LLMs at the token level. We assess the effectiveness of ETPO within a simulated environment that models data science code generation as a series of multi-step interactive tasks.
  arXiv  Detail & Related papers  (2024-02-09T07:45:26Z)
• GQE-PRF: Generative Query Expansion with Pseudo-Relevance Feedback [8.142861977776256]
  We propose a novel approach which effectively integrates text generation models into PRF-based query expansion. Our approach generates augmented query terms via neural text generation models conditioned on both the initial query and pseudo-relevance feedback. We evaluate the performance of our approach on information retrieval tasks using two benchmark datasets.
  arXiv  Detail & Related papers  (2021-08-13T01:09:02Z)

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.