Papers with unsupervised fine-tuning
Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) encapsulate a vast amount of factual information within their pre-trained weights. |
| Approach: | They compare unsupervised fine-tuning and retrieval-augmented generation approaches to learning new factual information. |
| Outcome: | The proposed models outperform unsupervised fine-tuning and retrieval-augmented generation (RAG) on knowledge-intensive tasks across different topics. |
Cross-lingual Multimodal Sentiment Analysis for Low-Resource Languages via Language Family Disentanglement and Rethinking Transfer (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing multimodal sentiment analysis methods are limited to textual data and cannot handle multimodal scenarios. |
| Approach: | They propose a transfer learning framework that allows cross-lingual and cross-modal alignments and a language family disentanglement module that enhances the sharing of language universals within families. |
| Outcome: | The proposed method is superior to existing methods and can handle low-resource languages. |
Contract Discovery: Dataset and a Few-Shot Semantic Retrieval Challenge with Competitive Baselines (2020.findings-emnlp)
Copied to clipboard
Łukasz Borchmann, Dawid Wisniewski, Andrzej Gretkowski, Izabela Kosmala, Dawid Jurkiewicz, Łukasz Szałkiewicz, Gabriela Pałka, Karol Kaczmarek, Agnieszka Kaliska, Filip Graliński
| Challenge: | Existing methods for detecting text fragments are not suitable for contract discovery, since it requires manual definition of a few examples, followed by conventional information. |
| Approach: | They propose a task where legal clauses are extracted from documents, given a few examples of similar clauses from other legal acts. |
| Outcome: | The proposed task differs substantially from conventional NLI and shared tasks on legal information extraction. |
Deductive Closure Training of Language Models for Coherence, Accuracy, and Updatability (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing language models (LMs) generate factually correct text and estimate truth values of individual claims, but they do not reflect a coherent, manipulable model of the world. |
| Approach: | They propose a method that uses language models to identify implications of (and contradictions within) the text they generate. |
| Outcome: | The proposed method improves LM factuality by 3-26% across the CREAK, MQuAKE, and Reversal Curse datasets. |
SPILL: Domain-Adaptive Intent Clustering based on Selection and Pooling with Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for intent clustering rely on labeled examples or unsupervised fine-tuning to optimize results for each new dataset. |
| Approach: | They propose a method that uses an embedder to derive an embedding for each utterance and then pool them with the seed to improve the embeddable results. |
| Outcome: | The proposed method outperforms embedding methods and is comparable to state-of-the-art methods. |
Financial Risk Relation Identification through Dual-view Adaptation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Identifying inter-firm risk relations is crucial for applications like portfolio management and investment strategy. |
| Approach: | They propose a method for extracting inter-firm risk relations using Form 10-K filings . their method captures implicit and abstract risk connections through unsupervised fine-tuning . |
| Outcome: | The proposed method outperforms baselines across multiple evaluation settings. |