# BCL: Bayesian In-Context Learning Framework for Information Extraction

arXiv: https://arxiv.org/abs/2606.18620 · HTML: https://mlsanity.com/paper/2606.18620/

## Key facts

- Cited by 1 papers 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 (most cited first, 23 of 23)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [A Tutorial on Bayesian Optimization](https://mlsanity.com/paper/1807.02811/) (2018)
- [Automatic Prompt Optimization with "Gradient Descent" and Beam Search](https://mlsanity.com/paper/2305.03495/) (2023)
- [Unified Demonstration Retriever for In-Context Learning](https://mlsanity.com/paper/2305.04320/) (2023)
- [Dr.ICL: Demonstration-Retrieved In-context Learning](https://mlsanity.com/paper/2305.14128/) (2023)
- [CodeIE: Large Code Generation Models are Better Few-Shot Information Extractors](https://mlsanity.com/paper/2305.05711/) (2023)
- [C-ICL: Contrastive In-context Learning for Information Extraction](https://mlsanity.com/paper/2402.11254/) (2024)
- [SciER: An Entity and Relation Extraction Dataset for Datasets, Methods, and Tasks in Scientific Documents](https://mlsanity.com/paper/2410.21155/) (2024)
- [A Simple but Effective Approach to Improve Structured Language Model Output for Information Extraction](https://mlsanity.com/paper/2402.13364/) (2024)
- [Intrinsic Entropy of Context Length Scaling in LLMs](https://mlsanity.com/paper/2502.01481/) (2025)
- [Bayesian Optimization for Controlled Image Editing via LLMs](https://mlsanity.com/paper/2502.18116/) (2025)
- [Attention Consistency for LLMs Explanation](https://mlsanity.com/paper/2509.17178/) (2025)
- [Retrieval--Reasoning Processes for Multi-hop Question Answering: A Four-Axis Design Framework and Empirical Trends](https://mlsanity.com/paper/2601.00536/) (2026)
- [Pretraining on the Test Set Is No Longer All You Need: A Debate-Driven Approach to QA Benchmarks](https://mlsanity.com/paper/2507.17747/) (2025)
- [Recall, Retrieve and Reason: Towards Better In-Context Relation Extraction](https://mlsanity.com/paper/2404.17809/) (2024)
- [Learning an Efficient Optimizer via Hybrid-Policy Sub-Trajectory Balance](https://mlsanity.com/paper/2511.00543/) (2025)
- [Is Meta-Learning Out? Rethinking Unsupervised Few-Shot Classification with Limited Entropy](https://mlsanity.com/paper/2509.13185/) (2025)
- [Discovering What You Can Control: Interventional Boundary Discovery for Reinforcement Learning](https://mlsanity.com/paper/2603.18257/) (2026)

## Built on by (most cited first, 1 of 1)

- [ES-VP : Energy-Shaped Dynamic Visual Prompting for Efficient Model Adaptation](https://mlsanity.com/paper/2608.21194/) (2026)

## 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.