BCL: Bayesian In-Context Learning Framework for Information Extraction
Not on the map. Why?
Abstract (arXiv)
Existing information extraction (IE) tasks increasingly adopt in-context learning (ICL) with large language models. However, current approaches either show inconsistent performance across model scales or lack systematic optimization and generalizability. Building on this, we propose BCL (Bayesian In-Context Learning Framework for Information Extraction), the first optimization framework that uses particle filtering with Bayesian updates to systematically refine label representations across IE tasks. Through four steps initialization, observation, weight update, and resampling, BCL generalizes to both sequence labeling and relation classification paradigms. Extensive experiments demonstrate substantial and consistent improvements over existing approaches.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 23 of its 49 references that are in the map. First posted on arXiv 17 Jun 2026.
Builds on
23 of 49 references.
References · 23
- 2020Language Models are Few-Shot Learnerscited by 32,419
- 2022Training language models to follow instructions with human feedbackcited by 15,971
- 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
- 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
- 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,434
- 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,392
- 2018A Tutorial on Bayesian Optimizationcited by 744
- 2023Automatic Prompt Optimization with "Gradient Descent" and Beam Searchcited by 653
- 2023Unified Demonstration Retriever for In-Context Learningcited by 142
- 2023Dr.ICL: Demonstration-Retrieved In-context Learningcited by 72
- 2023CodeIE: Large Code Generation Models are Better Few-Shot Information Extractorscited by 68
- 2024C-ICL: Contrastive In-context Learning for Information Extractioncited by 23
11 more
- 2024SciER: An Entity and Relation Extraction Dataset for Datasets, Methods, and Tasks in Scientific Documentscited by 21
- 2024A Simple but Effective Approach to Improve Structured Language Model Output for Information Extractioncited by 16
- 2025Intrinsic Entropy of Context Length Scaling in LLMscited by 14
- 2025Bayesian Optimization for Controlled Image Editing via LLMscited by 11
- 2025Attention Consistency for LLMs Explanationcited by 11
- 2026Retrieval--Reasoning Processes for Multi-hop Question Answering: A Four-Axis Design Framework and Empirical Trendscited by 8
- 2025Pretraining on the Test Set Is No Longer All You Need: A Debate-Driven Approach to QA Benchmarkscited by 7
- 2024Recall, Retrieve and Reason: Towards Better In-Context Relation Extractioncited by 6
- 2025Learning an Efficient Optimizer via Hybrid-Policy Sub-Trajectory Balancecited by 5
- 2025Is Meta-Learning Out? Rethinking Unsupervised Few-Shot Classification with Limited Entropycited by 4
- 2026Discovering What You Can Control: Interventional Boundary Discovery for Reinforcement Learningcited by 2
Built on by
Citing papers per year: 2026: 1.
1 paper.