Following the Autoregressive Nature of LLM Embeddings via Compression and Alignment

• URL: http://arxiv.org/abs/2502.11401v1
• Date: Mon, 17 Feb 2025 03:36:25 GMT
• Title: Following the Autoregressive Nature of LLM Embeddings via Compression and Alignment
• Authors: Jingcheng Deng, Zhongtao Jiang, Liang Pang, Liwei Chen, Kun Xu, Zihao Wei, Huawei Shen, Xueqi Cheng,
• Abstract summary: We propose AutoRegEmbed, a contrastive learning method built on embedding conditional probability distributions. We show that our method significantly outperforms traditional contrastive learning approaches.
• Score: 69.67015515485349
• License:
• Abstract: A new trend uses LLMs as dense text encoders via contrastive learning. However, since LLM embeddings predict the probability distribution of the next token, they are inherently generative and distributive, conflicting with contrastive learning, which requires embeddings to capture full-text semantics and align via cosine similarity. This discrepancy hinders the full utilization of LLMs' pre-training capabilities, resulting in inefficient learning. In response to this issue, we propose AutoRegEmbed, a new contrastive learning method built on embedding conditional probability distributions, which integrates two core tasks: information compression and conditional distribution alignment. The information compression task encodes text into the embedding space, ensuring that the embedding vectors capture global semantics. The conditional distribution alignment task focuses on aligning text embeddings with positive samples embeddings by leveraging the conditional distribution of embeddings while simultaneously reducing the likelihood of generating negative samples from text embeddings, thereby achieving embedding alignment and uniformity. Experimental results demonstrate that our method significantly outperforms traditional contrastive learning approaches and achieves performance comparable to state-of-the-art models when using the same amount of data.

Related papers

• Enhancing Input-Label Mapping in In-Context Learning with Contrastive Decoding [71.01099784480597]
  Large language models (LLMs) excel at a range of tasks through in-context learning (ICL) We introduce In-Context Contrastive Decoding (ICCD), a novel method that emphasizes input-label mapping. ICCD emphasizes input-label mapping by contrasting the output distributions between positive and negative in-context examples.
  arXiv  Detail & Related papers  (2025-02-19T14:04:46Z)
• Discriminative Representation learning via Attention-Enhanced Contrastive Learning for Short Text Clustering [1.6788443047694643]
  We propose a novel short text clustering method, called Discriminative Representation learning via textbfAttention-textbfEnhanced textbfContrastive textbfL. Experimental results demonstrate that the proposed textbfAECL outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-01-07T07:17:04Z)
• ItTakesTwo: Leveraging Peer Representations for Semi-supervised LiDAR Semantic Segmentation [24.743048965822297]
  This paper introduces a novel semi-supervised LiDAR semantic segmentation framework called ItTakesTwo (IT2) IT2 is designed to ensure consistent predictions from peer LiDAR representations, thereby improving the perturbation effectiveness in consistency learning. Results on public benchmarks show that our approach achieves remarkable improvements over the previous state-of-the-art (SOTA) methods in the field.
  arXiv  Detail & Related papers  (2024-07-09T18:26:53Z)
• Entropy Law: The Story Behind Data Compression and LLM Performance [115.70395740286422]
  We find that model performance is negatively correlated to the compression ratio of training data, which usually yields a lower training loss. Based on the findings of the entropy law, we propose a quite efficient and universal data selection method. We also present an interesting application of entropy law that can detect potential performance risks at the beginning of model training.
  arXiv  Detail & Related papers  (2024-07-09T08:14:29Z)
• Noisy Correspondence Learning with Self-Reinforcing Errors Mitigation [63.180725016463974]
  Cross-modal retrieval relies on well-matched large-scale datasets that are laborious in practice. We introduce a novel noisy correspondence learning framework, namely textbfSelf-textbfReinforcing textbfErrors textbfMitigation (SREM)
  arXiv  Detail & Related papers  (2023-12-27T09:03:43Z)
• ProbVLM: Probabilistic Adapter for Frozen Vision-Language Models [69.50316788263433]
  We propose ProbVLM, a probabilistic adapter that estimates probability distributions for the embeddings of pre-trained vision-language models. We quantify the calibration of embedding uncertainties in retrieval tasks and show that ProbVLM outperforms other methods. We present a novel technique for visualizing the embedding distributions using a large-scale pre-trained latent diffusion model.
  arXiv  Detail & Related papers  (2023-07-01T18:16:06Z)
• Distinguishability Calibration to In-Context Learning [31.375797763897104]
  We propose a method to map a PLM-encoded embedding into a new metric space to guarantee the distinguishability of the resulting embeddings. We also take the advantage of hyperbolic embeddings to capture the hierarchical relations among fine-grained class-associated token embedding.
  arXiv  Detail & Related papers  (2023-02-13T09:15:00Z)
• Trash to Treasure: Harvesting OOD Data with Cross-Modal Matching for Open-Set Semi-Supervised Learning [101.28281124670647]
  Open-set semi-supervised learning (open-set SSL) investigates a challenging but practical scenario where out-of-distribution (OOD) samples are contained in the unlabeled data. We propose a novel training mechanism that could effectively exploit the presence of OOD data for enhanced feature learning. Our approach substantially lifts the performance on open-set SSL and outperforms the state-of-the-art by a large margin.
  arXiv  Detail & Related papers  (2021-08-12T09:14:44Z)
• Disentangled Contrastive Learning for Learning Robust Textual Representations [13.880693856907037]
  We introduce the concept of momentum representation consistency to align features and leverage power normalization while conforming the uniformity. Our experimental results for the NLP benchmarks demonstrate that our approach can obtain better results compared with the baselines.
  arXiv  Detail & Related papers  (2021-04-11T03:32:49Z)

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.