Simple Techniques for Enhancing Sentence Embeddings in Generative Language Models

• URL: http://arxiv.org/abs/2404.03921v2
• Date: Wed, 15 May 2024 13:34:14 GMT
• Title: Simple Techniques for Enhancing Sentence Embeddings in Generative Language Models
• Authors: Bowen Zhang, Kehua Chang, Chunping Li,
• Abstract summary: Sentence embedding is a fundamental task within the realm of Natural Language Processing, finding extensive application in search engines, expert systems, and question-and-answer platforms. With the continuous evolution of large language models such as LLaMA and Mistral, research on sentence embedding has recently achieved notable breakthroughs. We propose two innovative prompt engineering techniques capable of further enhancing the expressive power of PLMs' raw embeddings.
• Score: 3.0566617373924325
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Sentence Embedding stands as a fundamental task within the realm of Natural Language Processing, finding extensive application in search engines, expert systems, and question-and-answer platforms. With the continuous evolution of large language models such as LLaMA and Mistral, research on sentence embedding has recently achieved notable breakthroughs. However, these advancements mainly pertain to fine-tuning scenarios, leaving explorations into computationally efficient direct inference methods for sentence representation in a nascent stage. This paper endeavors to bridge this research gap. Through comprehensive experimentation, we challenge the widely held belief in the necessity of an Explicit One-word Limitation for deriving sentence embeddings from Pre-trained Language Models (PLMs). We demonstrate that this approach, while beneficial for generative models under direct inference scenario, is not imperative for discriminative models or the fine-tuning of generative PLMs. This discovery sheds new light on the design of manual templates in future studies. Building upon this insight, we propose two innovative prompt engineering techniques capable of further enhancing the expressive power of PLMs' raw embeddings: Pretended Chain of Thought and Knowledge Enhancement. We confirm their effectiveness across various PLM types and provide a detailed exploration of the underlying factors contributing to their success.

Related papers

• From Linguistic Giants to Sensory Maestros: A Survey on Cross-Modal Reasoning with Large Language Models [56.9134620424985]
  Cross-modal reasoning (CMR) is increasingly recognized as a crucial capability in the progression toward more sophisticated artificial intelligence systems. The recent trend of deploying Large Language Models (LLMs) to tackle CMR tasks has marked a new mainstream of approaches for enhancing their effectiveness. This survey offers a nuanced exposition of current methodologies applied in CMR using LLMs, classifying these into a detailed three-tiered taxonomy.
  arXiv  Detail & Related papers  (2024-09-19T02:51:54Z)
• A Comprehensive Survey of Accelerated Generation Techniques in Large Language Models [2.091322528026356]
  This paper presents a survey of accelerated generation techniques in autoregressive language models. We categorize these techniques into several key areas: speculative decoding, early exiting mechanisms, and non-autoregressive methods.
  arXiv  Detail & Related papers  (2024-05-15T07:36:56Z)
• ChatGPT Alternative Solutions: Large Language Models Survey [0.0]
  Large Language Models (LLMs) have ignited a surge in research contributions within this domain. Recent years have witnessed a dynamic synergy between academia and industry, propelling the field of LLM research to new heights. This survey furnishes a well-rounded perspective on the current state of generative AI, shedding light on opportunities for further exploration, enhancement, and innovation.
  arXiv  Detail & Related papers  (2024-03-21T15:16:50Z)
• Supervised Knowledge Makes Large Language Models Better In-context Learners [94.89301696512776]
  Large Language Models (LLMs) exhibit emerging in-context learning abilities through prompt engineering. The challenge of improving the generalizability and factuality of LLMs in natural language understanding and question answering remains under-explored. We propose a framework that enhances the reliability of LLMs as it: 1) generalizes out-of-distribution data, 2) elucidates how LLMs benefit from discriminative models, and 3) minimizes hallucinations in generative tasks.
  arXiv  Detail & Related papers  (2023-12-26T07:24:46Z)
• A Survey on Prompting Techniques in LLMs [0.0]
  Autoregressive Large Language Models have transformed the landscape of Natural Language Processing. We present a taxonomy of existing literature on prompting techniques and provide a concise survey based on this taxonomy. We identify some open problems in the realm of prompting in autoregressive LLMs which could serve as a direction for future research.
  arXiv  Detail & Related papers  (2023-11-28T17:56:34Z)
• Large Language Models can Contrastively Refine their Generation for Better Sentence Representation Learning [57.74233319453229]
  Large language models (LLMs) have emerged as a groundbreaking technology and their unparalleled text generation capabilities have sparked interest in their application to the fundamental sentence representation learning task. We propose MultiCSR, a multi-level contrastive sentence representation learning framework that decomposes the process of prompting LLMs to generate a corpus. Our experiments reveal that MultiCSR enables a less advanced LLM to surpass the performance of ChatGPT, while applying it to ChatGPT achieves better state-of-the-art results.
  arXiv  Detail & Related papers  (2023-10-17T03:21:43Z)
• Improving Factuality and Reasoning in Language Models through Multiagent Debate [95.10641301155232]
  We present a complementary approach to improve language responses where multiple language model instances propose and debate their individual responses and reasoning processes over multiple rounds to arrive at a common final answer. Our findings indicate that this approach significantly enhances mathematical and strategic reasoning across a number of tasks. Our approach may be directly applied to existing black-box models and uses identical procedure and prompts for all tasks we investigate.
  arXiv  Detail & Related papers  (2023-05-23T17:55:11Z)
• A Survey of Large Language Models [81.06947636926638]
  Language modeling has been widely studied for language understanding and generation in the past two decades. Recently, pre-trained language models (PLMs) have been proposed by pre-training Transformer models over large-scale corpora. To discriminate the difference in parameter scale, the research community has coined the term large language models (LLM) for the PLMs of significant size.
  arXiv  Detail & Related papers  (2023-03-31T17:28:46Z)
• LMPriors: Pre-Trained Language Models as Task-Specific Priors [78.97143833642971]
  We develop principled techniques for augmenting our models with suitable priors. This is to encourage them to learn in ways that are compatible with our understanding of the world. We draw inspiration from the recent successes of large-scale language models (LMs) to construct task-specific priors distilled from the rich knowledge of LMs.
  arXiv  Detail & Related papers  (2022-10-22T19:09:18Z)
• Knowledge Enhanced Pretrained Language Models: A Compreshensive Survey [8.427521246916463]
  Pretrained Language Models (PLM) have established a new paradigm through learning informative representations on large-scale text corpus. This new paradigm has revolutionized the entire field of natural language processing, and set the new state-of-the-art performance for a wide variety of NLP tasks. To address this issue, integrating knowledge into PLMs have recently become a very active research area and a variety of approaches have been developed.
  arXiv  Detail & Related papers  (2021-10-16T03:27:56Z)

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.