Papers with LCG
Lexicon-Level Contrastive Visual-Grounding Improves Language Modeling (2024.findings-acl)
Copied to clipboard
| Challenge: | Neural language models (LMs) are trained on orders of magnitude more language data than human language learners receive, but without supervision from other sensory modalities that play a crucial role in human learning. |
| Approach: | They propose a grounded language learning procedure that leverages visual supervision to improve textual representations. |
| Outcome: | The proposed procedure outperforms standard language-only models in terms of learning efficiency in small and developmentally plausible data regimes and improves perplexity by around 5% on multiple language modeling tasks compared to other models trained on the same amount of text data. |
LLM-supertagger: Categorial Grammar Supertagging via Large Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Recent studies have shown that LLMs are underperforming in classification tasks due to their decoder-based nature. |
| Approach: | They propose a method that significantly boosts LLMs' performance in supertagging for both Combinatory Categorial Grammar (CCG) and Lambek Categorian Grammar (LCG). |
| Outcome: | The proposed method outperforms LSTM and encoder-based models and achieves state-of-the-art performance. |
Create! Don’t Repeat: A Paradigm Shift in Multi-Label Augmentation through Label Creative Generation (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing methods for multi-label data augmentation have been ineffective, authors say . a mere 1.5% of labels have more than 100 training instances, a problem that persists for years . |
| Approach: | They propose a new paradigm for multi-label data augmentation called Label Creative Generation . they propose tail-driven conditional augmentation with tail-based sampling and label-conditioned generation . |
| Outcome: | The proposed approach has shown a 10% increase in PSP@1 across three datasets . it effectively mitigates the long-tail effect and enhances model performance . |
Low-Confidence Gold: Refining Low-Confidence Samples for Efficient Instruction Tuning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Low-Confidence Gold (LCG) is a new filtering framework for Large Language Models that curates high-quality subsets while preserving data diversity. |
| Approach: | They propose a new filtering framework that employs centroid-based clustering and confidence-guided selection for identifying valuable instruction pairs. |
| Outcome: | The proposed framework improves performance on a subset of 6K samples while maintaining data diversity. |
Control Large Language Models via Divide and Conquer (2024.emnlp-main)
Copied to clipboard
| Challenge: | Lexically Constrained Generation (LCG) is a crucial task of text generation. |
| Approach: | They propose a Divide and Conquer Generation strategy to enhance LLMs' performance in Lexically Constrained Generation with prompt-based controlling. |
| Outcome: | The proposed strategy shows 90% improvement on the most challenging LCG task. |
LCGbank: A Corpus of Syntactic Analyses Based on Proof Nets (2024.lrec-main)
Copied to clipboard
| Challenge: | Recent studies have focused on statistical syntactic parsing with proof nets . however, there has been a paucity of corpora in formalisms for which proof net is applicable . |
| Approach: | They propose a corpus of syntactic analyses based on Lambek categorial grammar . they leverage the relationship between LCG and CCG to address this problem . |
| Outcome: | The proposed method exploits the relationship between LCG and CCG to build an English-language corpus of syntactic analyses based on proof nets . the results suggest that the proposed method is weakly context-free equivalent and NP-complete . |