Papers with LLM-
Automatic Transmission for LLM Tiers: Optimizing Cost and Accuracy in Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are powerful tools for a wide range of natural language tasks. |
| Approach: | They propose an LLM automatic transmission framework that automatically selects LLM tiers without training. |
| Outcome: | The proposed framework achieves superior performance while reducing costs. |
An LLM-Embedding Semantic Adaptation Network for Post-level Semantic Drift Evaluation (2026.findings-acl)
Copied to clipboard
| Challenge: | Evaluating semantic drift is essential for understanding discourse evolution and opinion formation in online discussions. |
| Approach: | They propose an LLM-embedding Semantic Adaptation Network to evaluate semantic drift . they use an LRU module, an LEM-Embedding graph convolutional network module and an adaptive fusion module to integrate features from event related posts. |
| Outcome: | The proposed model achieves state-of-the-art performance on the semantic drift evaluation task compared to baseline models. |
Towards Event Extraction with Massive Types: LLM-based Collaborative Annotation and Partitioning Extraction (2025.emnlp-main)
Copied to clipboard
| Challenge: | Event Extraction (EE) is a long-standing target, but lacks an efficient and effective annotation framework to construct the corresponding datasets. |
| Approach: | They propose an LLM-based collaborative annotation framework that refines annotations of triggers from distant supervision and carries out argument annotation. |
| Outcome: | The proposed framework outperforms state-of-the-art methods on the largest EE dataset to date . it achieves the F1 scores of 90% and 85.3% on the human-annotated test set . |
Confidence-Aware Ranker Ensembles for Robust In-Context Knowledge Editing (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models excel at factual recall, but can propagate stale or incorrect knowledge. |
| Approach: | They propose a feature-weighted ensemble for in-context knowledge editing that calibrates three heterogeneous rankers and extracts simple confidence features from each ranker. |
| Outcome: | The proposed method achieves 88.33% Edit-Success Rate over the best single retriever . it improves edit accuracy without touching model weights and approaches oracle upper bound (91%). |