Let LLMs Speak Embedding Languages: Generative Text Embeddings via Iterative Contrastive Refinement

• URL: http://arxiv.org/abs/2509.24291v1
• Date: Mon, 29 Sep 2025 05:09:08 GMT
• Title: Let LLMs Speak Embedding Languages: Generative Text Embeddings via Iterative Contrastive Refinement
• Abstract summary: We introduce GIRCSE (Generative Iterative Refinement for Contrastive Sentence Embeddings), a novel framework that leverages autoregressive generation to iteratively refine semantic representations.<n>Our results establish generative iterative refinement as a new paradigm for representation learning.
• Score: 5.580772351753706
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Existing large language model (LLM)-based embeddings typically adopt an encoder-only paradigm, treating LLMs as static feature extractors and overlooking their core generative strengths. We introduce GIRCSE (Generative Iterative Refinement for Contrastive Sentence Embeddings), a novel framework that leverages autoregressive generation to iteratively refine semantic representations. By producing sequences of soft tokens optimized under contrastive objective, GIRCSE captures latent concepts and implicit semantics that encoder-only methods often miss. To guide this process, we propose an Iterative Contrastive Refinement (ICR) objective that encourages each refinement step to yield better representations. Extensive experiments show that GIRCSE outperforms strong LLM-based embedding baselines on the MTEB benchmark and instruction-following tasks. Moreover, GIRCSE exhibits an emergent test-time scaling property: generating more tokens at inference steadily improves embedding quality. Our results establish generative iterative refinement as a new paradigm for representation learning.

Related papers

• InsightSR: Refining Symbolic Regression Search Spaces via Parallel Semantic and Structural LLM Guidance [8.272456038469484]
  Symbolic regression seeks to discover parsimonious mathematical laws from observational data.<n>We present InsightSR, a framework that embeds Large Language Models (LLMs) iteration as a guiding layer around the PySR genetic programming engine.
  arXiv  Detail & Related papers  (2026-08-26T02:04:20Z)
• Learning to Label: A Reinforced Self-Evolving Framework for Semi-supervised Referring Expression Segmentation [34.401271440453044]
  Learning to Label casts pseudo-label construction as a learnable decision-making process.<n>To ensure stable learning, reinforced pseudo-label selection is formulated as an exploratory decision process.<n>Experiments on RefCOCO, RefCO+, and RefCOCOg demonstrate improvements over existing methods.
  arXiv  Detail & Related papers  (2026-05-27T09:54:26Z)
• Scaling Language-Centric Omnimodal Representation Learning [26.999264997449586]
  multimodal embedding approaches leveraging large language models (MLLMs) fine-tuned with contrastive learning (CL) have shown promising results.<n>This work argues that a crucial advantage of MLLM-based approaches stems from implicit cross-modal alignment achieved during generative pretraining.<n>We propose a Language-Centric Omnimodal Embedding framework, termed LCO-Emb.
  arXiv  Detail & Related papers  (2025-10-13T17:53:52Z)
• Growing Visual Generative Capacity for Pre-Trained MLLMs [60.826355079902505]
  Bridge is a pure autoregressive unified MLLM that augments pre-trained visual understanding models with generative ability.<n>We propose a semantic-to-pixel discrete representation that integrates compact semantic tokens with fine-grained pixel tokens.
  arXiv  Detail & Related papers  (2025-10-02T00:40:02Z)
• Refining Sentence Embedding Model through Ranking Sentences Generation with Large Language Models [60.00178316095646]
  Sentence embedding is essential for many NLP tasks, with contrastive learning methods achieving strong performance using datasets like NLI.<n>Recent studies leverage large language models (LLMs) to generate sentence pairs, reducing annotation dependency.<n>We propose a method for controlling the generation direction of LLMs in the latent space. Unlike unconstrained generation, the controlled approach ensures meaningful semantic divergence.<n> Experiments on multiple benchmarks demonstrate that our method achieves new SOTA performance with a modest cost in ranking sentence synthesis.
  arXiv  Detail & Related papers  (2025-02-19T12:07:53Z)
• Retrieval-Augmented Semantic Parsing: Improving Generalization with Lexical Knowledge [6.948555996661213]
  We introduce Retrieval-Augmented Semantic Parsing (RASP), a simple yet effective approach that integrates external symbolic knowledge into the parsing process.<n>Our experiments show that LLMs outperform previous encoder-decoder baselines for semantic parsing.<n>RASP further enhances their ability to predict unseen concepts, nearly doubling the performance of previous models on out-of-distribution concepts.
  arXiv  Detail & Related papers  (2024-12-13T15:30:20Z)
• Align-SLM: Textless Spoken Language Models with Reinforcement Learning from AI Feedback [50.84142264245052]
  This work introduces the Align-SLM framework to enhance the semantic understanding of textless Spoken Language Models (SLMs)<n>Our approach generates multiple speech continuations from a given prompt and uses semantic metrics to create preference data for Direct Preference Optimization (DPO)<n>We evaluate the framework using ZeroSpeech 2021 benchmarks for lexical and syntactic modeling, the spoken version of the StoryCloze dataset for semantic coherence, and other speech generation metrics, including the GPT4-o score and human evaluation.
  arXiv  Detail & Related papers  (2024-11-04T06:07:53Z)
• 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.<n>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)
• Reconsidering Degeneration of Token Embeddings with Definitions for Encoder-based Pre-trained Language Models [20.107727903240065]
  We propose DefinitionEMB to re-construct isotropically distributed and semantics-related token embeddings for encoder-based language models. Our experiments demonstrate the effectiveness of leveraging definitions from Wiktionary to re-construct such embeddings.
  arXiv  Detail & Related papers  (2024-08-02T15:00:05Z)
• Prompt Perturbation in Retrieval-Augmented Generation based Large Language Models [9.688626139309013]
  Retrieval-Augmented Generation is considered as a means to improve the trustworthiness of text generation from large language models. In this work, we find that the insertion of even a short prefix to the prompt leads to the generation of outputs far away from factually correct answers. We introduce a novel optimization technique called Gradient Guided Prompt Perturbation.
  arXiv  Detail & Related papers  (2024-02-11T12:25:41Z)
• 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)
• Scalable Learning of Latent Language Structure With Logical Offline Cycle Consistency [71.42261918225773]
  Conceptually, LOCCO can be viewed as a form of self-learning where the semantic being trained is used to generate annotations for unlabeled text. As an added bonus, the annotations produced by LOCCO can be trivially repurposed to train a neural text generation model.
  arXiv  Detail & Related papers  (2023-05-31T16:47:20Z)
• Semantics-Aware Dynamic Localization and Refinement for Referring Image Segmentation [102.25240608024063]
  Referring image segments an image from a language expression. We develop an algorithm that shifts from being localization-centric to segmentation-language. Compared to its counterparts, our method is more versatile yet effective.
  arXiv  Detail & Related papers  (2023-03-11T08:42:40Z)

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.