Policy-Gradient Training of Language Models for Ranking

• URL: http://arxiv.org/abs/2310.04407v2
• Date: Sat, 23 Nov 2024 16:00:51 GMT
• Title: Policy-Gradient Training of Language Models for Ranking
• Authors: Ge Gao, Jonathan D. Chang, Claire Cardie, Kianté Brantley, Thorsten Joachim,
• Abstract summary: Text retrieval plays a crucial role in incorporating factual knowledge for decision making into language processing pipelines. Current state-of-the-art text retrieval models leverage pre-trained large language models (LLMs) to achieve competitive performance. We introduce Neural PG-RANK, a novel training algorithm that learns to rank by instantiating a LLM as a Plackett-Luce ranking policy.
• Score: 29.940468096858066
• License:
• Abstract: Text retrieval plays a crucial role in incorporating factual knowledge for decision making into language processing pipelines, ranging from chat-based web search to question answering systems. Current state-of-the-art text retrieval models leverage pre-trained large language models (LLMs) to achieve competitive performance, but training LLM-based retrievers via typical contrastive losses requires intricate heuristics, including selecting hard negatives and using additional supervision as learning signals. This reliance on heuristics stems from the fact that the contrastive loss itself is heuristic and does not directly optimize the downstream metrics of decision quality at the end of the processing pipeline. To address this issue, we introduce Neural PG-RANK, a novel training algorithm that learns to rank by instantiating a LLM as a Plackett-Luce ranking policy. Neural PG-RANK provides a principled method for end-to-end training of retrieval models as part of larger decision systems via policy gradient, with little reliance on complex heuristics, and it effectively unifies the training objective with downstream decision-making quality. We conduct extensive experiments on various text retrieval benchmarks. The results demonstrate that when the training objective aligns with the evaluation setup, Neural PG-RANK yields remarkable in-domain performance improvement, with substantial out-of-domain generalization to some critical datasets employed in downstream question answering tasks.

Related papers

• Deciphering Cross-Modal Alignment in Large Vision-Language Models with Modality Integration Rate [118.37653302885607]
  We present the Modality Integration Rate (MIR), an effective, robust, and generalized metric to indicate the multi-modal pre-training quality of Large Vision Language Models (LVLMs) MIR is indicative about training data selection, training strategy schedule, and model architecture design to get better pre-training results.
  arXiv  Detail & Related papers  (2024-10-09T17:59:04Z)
• Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG [36.754491649652664]
  Retrieval-augmented generation (RAG) empowers large language models (LLMs) to utilize external knowledge sources. This paper investigates the detrimental impact of retrieved "hard negatives" as a key contributor. To mitigate this and enhance the robustness of long-context LLM-based RAG, we propose both training-free and training-based approaches.
  arXiv  Detail & Related papers  (2024-10-08T12:30:07Z)
• Efficient Recurrent Off-Policy RL Requires a Context-Encoder-Specific Learning Rate [4.6659670917171825]
  Recurrent reinforcement learning (RL) consists of a context encoder based on recurrent neural networks (RNNs) for unobservable state prediction. Previous RL methods face training stability issues due to the gradient instability of RNNs. We propose Recurrent Off-policy RL with Context-Encoder-Specific Learning Rate (RESeL) to tackle this issue.
  arXiv  Detail & Related papers  (2024-05-24T09:33:47Z)
• Unsupervised Pre-training with Language-Vision Prompts for Low-Data Instance Segmentation [105.23631749213729]
  We propose a novel method for unsupervised pre-training in low-data regimes. Inspired by the recently successful prompting technique, we introduce a new method, Unsupervised Pre-training with Language-Vision Prompts. We show that our method can converge faster and perform better than CNN-based models in low-data regimes.
  arXiv  Detail & Related papers  (2024-05-22T06:48:43Z)
• Decentralized Learning Strategies for Estimation Error Minimization with Graph Neural Networks [94.2860766709971]
  We address the challenge of sampling and remote estimation for autoregressive Markovian processes in a wireless network with statistically-identical agents. Our goal is to minimize time-average estimation error and/or age of information with decentralized scalable sampling and transmission policies.
  arXiv  Detail & Related papers  (2024-04-04T06:24:11Z)
• How Can LLM Guide RL? A Value-Based Approach [68.55316627400683]
  Reinforcement learning (RL) has become the de facto standard practice for sequential decision-making problems by improving future acting policies with feedback. Recent developments in large language models (LLMs) have showcased impressive capabilities in language understanding and generation, yet they fall short in exploration and self-improvement capabilities. We develop an algorithm named LINVIT that incorporates LLM guidance as a regularization factor in value-based RL, leading to significant reductions in the amount of data needed for learning.
  arXiv  Detail & Related papers  (2024-02-25T20:07:13Z)
• Take the Bull by the Horns: Hard Sample-Reweighted Continual Training Improves LLM Generalization [165.98557106089777]
  A key challenge is to enhance the capabilities of large language models (LLMs) amid a looming shortage of high-quality training data. Our study starts from an empirical strategy for the light continual training of LLMs using their original pre-training data sets. We then formalize this strategy into a principled framework of Instance-Reweighted Distributionally Robust Optimization.
  arXiv  Detail & Related papers  (2024-02-22T04:10:57Z)
• 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)
• Aligning Language Models with Offline Learning from Human Feedback [5.539080592071948]
  We propose an offline learning from human feedback framework to align language models without interacting with environments. Specifically, we explore filtering alignment (FA), reward-weighted regression (RWR), and conditional alignment (CA) to align language models to human preferences.
  arXiv  Detail & Related papers  (2023-08-23T10:41:07Z)

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.