# Combining Distantly Supervised Models with In Context Learning for Monolingual and Cross-Lingual Relation Extraction

arXiv: https://arxiv.org/abs/2510.18344 · HTML: https://mlsanity.com/paper/2510.18344/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 32 references that are in the map.
- First posted on arXiv 21 Oct 2025.

## Builds on (most cited first, 19 of 19)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks](https://mlsanity.com/paper/2406.18403/) (2024)
- [IndicTrans2: Towards High-Quality and Accessible Machine Translation Models for all 22 Scheduled Indian Languages](https://mlsanity.com/paper/2305.16307/) (2023)
- [Coverage-based Example Selection for In-Context Learning](https://mlsanity.com/paper/2305.14907/) (2023)
- [IndicGenBench: A Multilingual Benchmark to Evaluate Generation Capabilities of LLMs on Indic Languages](https://mlsanity.com/paper/2404.16816/) (2024)
- [RESIDE: Improving Distantly-Supervised Neural Relation Extraction using Side Information](https://mlsanity.com/paper/1812.04361/) (2018)
- [Frustratingly Easy Label Projection for Cross-lingual Transfer](https://mlsanity.com/paper/2211.15613/) (2022)
- [CIL: Contrastive Instance Learning Framework for Distantly Supervised Relation Extraction](https://mlsanity.com/paper/2106.10855/) (2021)
- [Manual Evaluation Matters: Reviewing Test Protocols of Distantly Supervised Relation Extraction](https://mlsanity.com/paper/2105.09543/) (2021)
- [Exploring the Role of Diversity in Example Selection for In-Context Learning](https://mlsanity.com/paper/2505.01842/) (2025)
- [Grasping the Essentials: Tailoring Large Language Models for Zero-Shot Relation Extraction](https://mlsanity.com/paper/2402.11142/) (2024)
- [Effective Demonstration Annotation for In-Context Learning via Language Model-Based Determinantal Point Process](https://mlsanity.com/paper/2408.02103/) (2024)
- [A Data Bootstrapping Recipe for Low Resource Multilingual Relation Classification](https://mlsanity.com/paper/2110.09570/) (2021)
- [Constrained Decoding for Cross-lingual Label Projection](https://mlsanity.com/paper/2402.03131/) (2024)
- [Cross-Lingual Relation Extraction with Transformers](https://mlsanity.com/paper/2010.08652/) (2020)
- [SSP: Self-Supervised Prompting for Cross-Lingual Transfer to Low-Resource Languages using Large Language Models](https://mlsanity.com/paper/2406.18880/) (2024)

## Abstract (arXiv)

Distantly Supervised Relation Extraction (DSRE) remains a long-standing challenge in NLP, where models must learn from noisy bag-level annotations while making sentence-level predictions. While existing state-of-the-art (SoTA) DSRE models rely on task-specific training, their integration with in-context learning (ICL) using large language models (LLMs) remains underexplored. A key challenge is that the LLM may not learn relation semantics correctly, due to noisy annotation. In response, we propose HYDRE -- HYbrid Distantly Supervised Relation Extraction framework. It first uses a trained DSRE model to identify the top-k candidate relations for a given test sentence, then uses a novel dynamic exemplar retrieval strategy that extracts reliable, sentence-level exemplars from training data, which are then provided in LLM prompt for outputting the final relation(s). We further extend HYDRE to cross-lingual settings for RE in low-resource languages. Using available English DSRE training data, we evaluate all methods on English as well as a newly curated benchmark covering four diverse low-resource Indic languages -- Oriya, Santali, Manipuri, and Tulu. HYDRE achieves up to 20 F1 point gains in English and, on average, 17 F1 points on Indic languages over prior SoTA DSRE models. Detailed ablations exhibit HYDRE's efficacy compared to other prompting strategies.