OneGen: Efficient One-Pass Unified Generation and Retrieval for LLMs

• URL: http://arxiv.org/abs/2409.05152v2
• Date: Wed, 2 Oct 2024 05:02:02 GMT
• Title: OneGen: Efficient One-Pass Unified Generation and Retrieval for LLMs
• Authors: Jintian Zhang, Cheng Peng, Mengshu Sun, Xiang Chen, Lei Liang, Zhiqiang Zhang, Jun Zhou, Huajun Chen, Ningyu Zhang,
• Abstract summary: One-pass Generation and retrieval framework (OneGen) OneGen bridges the traditionally separate training approaches for generation and retrieval by incorporating retrieval tokens generated autoregressively. Results show that integrating generation and retrieval within the same context preserves the generative capabilities of LLMs while improving retrieval performance.
• Score: 44.054569398300266
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite the recent advancements in Large Language Models (LLMs), which have significantly enhanced the generative capabilities for various NLP tasks, LLMs still face limitations in directly handling retrieval tasks. However, many practical applications demand the seamless integration of both retrieval and generation. This paper introduces a novel and efficient One-pass Generation and retrieval framework (OneGen), designed to improve LLMs' performance on tasks that require both generation and retrieval. The proposed framework bridges the traditionally separate training approaches for generation and retrieval by incorporating retrieval tokens generated autoregressively. This enables a single LLM to handle both tasks simultaneously in a unified forward pass. We conduct experiments on two distinct types of composite tasks, RAG and Entity Linking, to validate the pluggability, effectiveness, and efficiency of OneGen in training and inference. Furthermore, our results show that integrating generation and retrieval within the same context preserves the generative capabilities of LLMs while improving retrieval performance. To the best of our knowledge, OneGen is the first to enable LLMs to conduct vector retrieval during the generation.

Related papers

• Invar-RAG: Invariant LLM-aligned Retrieval for Better Generation [43.630437906898635]
  We propose a novel two-stage fine-tuning architecture called Invar-RAG. In the retrieval stage, an LLM-based retriever is constructed by integrating LoRA-based representation learning. In the generation stage, a refined fine-tuning method is employed to improve LLM accuracy in generating answers based on retrieved information.
  arXiv  Detail & Related papers  (2024-11-11T14:25:37Z)
• GenEOL: Harnessing the Generative Power of LLMs for Training-Free Sentence Embeddings [7.957874169275548]
  Training-free embedding methods directly leverage pretrained large language models (LLMs) to embed text. We propose a novel method, which uses LLMs to generate diverse transformations of a sentence that preserve its meaning.
  arXiv  Detail & Related papers  (2024-10-18T17:36:53Z)
• A + B: A General Generator-Reader Framework for Optimizing LLMs to Unleash Synergy Potential [20.1396255995056]
  Retrieval-Augmented Generation (RAG) is an effective solution to supplement necessary knowledge to large language models (LLMs) "generate-then-read" pipeline is proposed to replace the retrieval stage with generation from the LLM itself. This paper formalizes a general "A + B" framework with varying combinations of foundation models and types for systematic investigation.
  arXiv  Detail & Related papers  (2024-06-06T11:14:27Z)
• One Token Can Help! Learning Scalable and Pluggable Virtual Tokens for Retrieval-Augmented Large Language Models [67.49462724595445]
  Retrieval-augmented generation (RAG) is a promising way to improve large language models (LLMs) We propose a novel method that involves learning scalable and pluggable virtual tokens for RAG.
  arXiv  Detail & Related papers  (2024-05-30T03:44:54Z)
• Towards Modular LLMs by Building and Reusing a Library of LoRAs [64.43376695346538]
  We study how to best build a library of adapters given multi-task data. We introduce model-based clustering, MBC, a method that groups tasks based on the similarity of their adapter parameters. To re-use the library, we present a novel zero-shot routing mechanism, Arrow, which enables dynamic selection of the most relevant adapters.
  arXiv  Detail & Related papers  (2024-05-18T03:02:23Z)
• StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback [58.20547418182074]
  We introduce StepCoder, a novel framework for code generation, consisting of two main components. CCCS addresses the exploration challenge by breaking the long sequences code generation task into a Curriculum of Code Completion Subtasks. FGO only optimize the model by masking the unexecuted code segments to provide Fine-Grained Optimization. Our method improves the ability to explore the output space and outperforms state-of-the-art approaches in corresponding benchmarks.
  arXiv  Detail & Related papers  (2024-02-02T13:14:31Z)
• Knowledge Fusion of Large Language Models [73.28202188100646]
  This paper introduces the notion of knowledge fusion for large language models (LLMs) We externalize their collective knowledge and unique strengths, thereby elevating the capabilities of the target model beyond those of any individual source LLM. Our findings confirm that the fusion of LLMs can improve the performance of the target model across a range of capabilities such as reasoning, commonsense, and code generation.
  arXiv  Detail & Related papers  (2024-01-19T05:02:46Z)
• Instruction Fusion: Advancing Prompt Evolution through Hybridization [27.321629102942754]
  This paper examines the constraints of existing prompt evolution techniques and introduces a novel approach, Instruction Fusion (IF) IF innovatively combines two distinct prompts through a hybridization process, thereby enhancing the evolution of training prompts for code LLMs. Our experimental results reveal that the proposed novel method effectively addresses the shortcomings of prior methods, significantly improving the performance of Code LLMs.
  arXiv  Detail & Related papers  (2023-12-25T11:00:37Z)
• Text Generation with Efficient (Soft) Q-Learning [91.47743595382758]
  Reinforcement learning (RL) offers a more flexible solution by allowing users to plug in arbitrary task metrics as reward. We introduce a new RL formulation for text generation from the soft Q-learning perspective. We apply the approach to a wide range of tasks, including learning from noisy/negative examples, adversarial attacks, and prompt generation.
  arXiv  Detail & Related papers  (2021-06-14T18:48:40Z)

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.