mlsanityData to 14 Oct 2026

Search-Adaptor: Embedding Customization for Information Retrieval

arXiv 2310.08750 ↗First posted 12 Oct 2023cs.LGcited by 11

Not on the map. Why?

Abstract (arXiv)

Embeddings extracted by pre-trained Large Language Models (LLMs) have significant potential to improve information retrieval and search. Beyond the zero-shot setup in which they are being conventionally used, being able to take advantage of the information from the relevant query-corpus paired data can further boost the LLM capabilities. In this paper, we propose a novel method, Search-Adaptor, for customizing LLMs for information retrieval in an efficient and robust way. Search-Adaptor modifies the embeddings generated by pre-trained LLMs, and can be integrated with any LLM, including those only available via prediction APIs. On multiple English, multilingual, and multimodal retrieval datasets, we show consistent and significant performance benefits for Search-Adaptor -- e.g., more than 5% improvements for Google Embedding APIs in nDCG@10 averaged over 14 BEIR datasets.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 24 of its 35 references that are in the map. First posted on arXiv 12 Oct 2023.

Builds on

24 of 35 references.

References · 24

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  4. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  5. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,236
  6. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,915
  7. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
  8. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,512
  9. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
  10. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,332
  11. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,253
  12. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,252
12 more
  1. 2021BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-modelscited by 1,245
  2. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,216
  3. 2022Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learningcited by 896
  4. 2023Towards General Text Embeddings with Multi-stage Contrastive Learningcited by 723
  5. 2021Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Modelscited by 463
  6. 2022One Embedder, Any Task: Instruction-Finetuned Text Embeddingscited by 333
  7. 2022Promptagator: Few-shot Dense Retrieval From 8 Examplescited by 235
  8. 2020AdapterDrop: On the Efficiency of Adapters in Transformerscited by 224
  9. 2023MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Usecited by 217
  10. 2021Condenser: a Pre-training Architecture for Dense Retrievalcited by 162
  11. 2017Automatic Spatially-aware Fashion Concept Discoverycited by 134
  12. 2022Making a MIRACL: Multilingual Information Retrieval Across a Continuum of Languagescited by 47

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 9.

11 papers.

  1. 2025SMEC: Rethinking Matryoshka Representation Learning for Retrieval Embedding Compressioncited by 14
  2. 2026IMRNNs: An Efficient Method for Interpretable Dense Retrieval via Embedding Modulationcited by 3
  3. 2026Succeeding at Scale: Enterprise Retrieval Benchmark Construction and Index-Preserving Query Adaptation for Multi-Tenant Searchcited by 2
  4. 2026Efficient Temporal-aware Matryoshka Adaptation for Temporal Information Retrievalcited by 2
  5. 2026Align Then Adapt: Label-Efficient Adapter Learning for Asymmetric Dense Retrievalcited by 2
  6. 2025ConceptCarve: Dynamic Realization of Evidencecited by 0
  7. 2026Learning to Select: Query-Aware Adaptive Dimension Selection for Dense Retrievalcited by 0
  8. 2026DIVE: Embedding Compression via Self-Limiting Gradient Updatescited by 0
  9. 2026When Does Dense Retrieval Need Asymmetric Geometry? A Bias-Variance Theory of Shared and Dual Projectionscited by 0
  10. 2026Madeleine: Learning Involuntary Recall for Conversational Memory from Simulated Livescited by 0
  11. 2026Beyond the Final Embedding: Retrieving Memories from Token-Level Evidencecited by 0