mlsanityData to 14 Oct 2026

BBox-Adapter: Lightweight Adapting for Black-Box Large Language Models

arXiv 2402.08219 ↗First posted 13 Feb 2024cs.CL cs.AI cs.LGcited by 11

Not on the map. Why?

Abstract (arXiv)

Adapting state-of-the-art Large Language Models (LLMs) like GPT-4 and Gemini for specific tasks is challenging. Due to the opacity in their parameters, embeddings, and even output probabilities, existing fine-tuning adaptation methods are inapplicable. Consequently, adapting these black-box LLMs is only possible through their API services, raising concerns about transparency, privacy, and cost. To address these challenges, we introduce BBox-Adapter, a novel lightweight adapter for black-box LLMs. BBox-Adapter distinguishes target and source domain data by treating target data as positive and source data as negative. It employs a ranking-based Noise Contrastive Estimation (NCE) loss to promote the likelihood of target domain data while penalizing that of the source domain. Furthermore, it features an online adaptation mechanism, which incorporates real-time positive data sampling from ground-truth, human, or AI feedback, coupled with negative data from previous adaptations. Extensive experiments demonstrate BBox-Adapter's effectiveness and cost efficiency. It improves model performance by up to 6.77% across diverse tasks and domains, while reducing training and inference costs by 31.30x and 1.84x, respectively.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 43 of its 57 references that are in the map. First posted on arXiv 13 Feb 2024.

Builds on

43 of 57 references.

References · 43

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  5. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  6. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  7. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  8. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  9. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,236
  10. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,915
  11. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
  12. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
31 more
  1. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  2. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 3,050
  3. 2022Scaling Instruction-Finetuned Language Modelscited by 3,024
  4. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,975
  5. 2022Language Models (Mostly) Know What They Knowcited by 1,856
  6. 2024Mixtral of Expertscited by 1,823
  7. 2020Don't Stop Pretraining: Adapt Language Models to Domains and Taskscited by 1,565
  8. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,407
  9. 2023PaLM 2 Technical Reportcited by 1,162
  10. 2021Towards a Unified View of Parameter-Efficient Transfer Learningcited by 872
  11. 2023ChatGPT Outperforms Crowd-Workers for Text-Annotation Taskscited by 870
  12. 2022Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Taskscited by 868
  13. 2023Reasoning with Language Model is Planning with World Modelcited by 861
  14. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 743
  15. 2023RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedbackcited by 625
  16. 2022ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detectioncited by 422
  17. 2022Black-Box Tuning for Language-Model-as-a-Servicecited by 256
  18. 2022Making Large Language Models Better Reasoners with Step-Aware Verifiercited by 233
  19. 2023Continual Pre-training of Language Modelscited by 198
  20. 2023Self-Evaluation Guided Beam Search for Reasoningcited by 196
  21. 2023Continual Pre-Training of Large Language Models: How to (re)warm your model?cited by 137
  22. 2018Noise Contrastive Estimation and Negative Sampling for Conditional Models: Consistency and Statistical Efficiencycited by 105
  23. 2023ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Searchcited by 105
  24. 2020Residual Energy-Based Models for Text Generationcited by 95
  25. 2022Solving Math Word Problems via Cooperative Reasoning induced Language Modelscited by 77
  26. 2023Making Large Language Models Better Reasoners with Alignmentcited by 63
  27. 2023Meta-Learning Online Adaptation of Language Modelscited by 43
  28. 2023Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuningcited by 33
  29. 2023CombLM: Adapting Black-Box Language Models through Small Fine-Tuned Modelscited by 26
  30. 2023kNN-Adapter: Efficient Domain Adaptation for Black-Box Language Modelscited by 14
  31. 2023PathFinder: Guided Search over Multi-Step Reasoning Pathscited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 6; 2026: 3.

11 papers.

  1. 2025PaperBench: Evaluating AI's Ability to Replicate AI Researchcited by 321
  2. 2025Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skillscited by 22
  3. 2025Learning from Diverse Reasoning Paths with Routing and Collaborationcited by 12
  4. 2024Matryoshka Pilot: Learning to Drive Black-Box LLMs with LLMscited by 9
  5. 2024PortLLM: Personalizing Evolving Large Language Models with Training-Free and Portable Model Patchescited by 7
  6. 2025Sysformer: Safeguarding Frozen Large Language Models with Adaptive System Promptscited by 5
  7. 2025DICE: Structured Reasoning in LLMs through SLM-Guided Chain-of-Thought Correctioncited by 2
  8. 2026Adapting in the Dark: Efficient and Stable Test-Time Adaptation for Black-Box Modelscited by 2
  9. 2026Beyond Learning: A Training-Free Alternative to Model Adaptationcited by 1
  10. 2025Make me an Expert: Distilling from Generalist Black-Box Models into Specialized Models for Semantic Segmentationcited by 0
  11. 2026Exploration-Driven Optimization for Test-Time Large Language Model Reasoningcited by 0