activity
20222024
most citedUnlocking Context Constraints of LLMs: Enhancing Context Efficiency of LLMs with Self-Information-Based Content Filtering

10 citations · 23 across the 9 of their papers we have counts for

collaborators

9 papers

cs.CL20242 cited

Evaluating Large Language Models for Generalization and Robustness via Data Compression

Yucheng Li, Yunhao Guo, Frank Guerin +1

Existing methods for evaluating large language models face challenges such as data contamination, sensitivity to prompts, and the high cost of benchmark creation. To address this,…

cs.CL2024

Finding Challenging Metaphors that Confuse Pretrained Language Models

Yucheng Li, Frank Guerin, Chenghua Lin

Metaphors are considered to pose challenges for a wide spectrum of NLP tasks. This gives rise to the area of computational metaphor processing. However, it remains unclear what typ…

cs.CL20234 cited

Estimating Contamination via Perplexity: Quantifying Memorisation in Language Model Evaluation

Yucheng Li

Data contamination in model evaluation is getting increasingly prevalent as the massive training corpora of large language models often unintentionally include benchmark samples. T…

cs.CL20231 cited

Metaphor Detection via Explicit Basic Meanings Modelling

Yucheng Li, Shun Wang, Chenghua Lin +1

One noticeable trend in metaphor detection is the embrace of linguistic theories such as the metaphor identification procedure (MIP) for model architecture design. While MIP clearl…

cs.CL202310 cited

Unlocking Context Constraints of LLMs: Enhancing Context Efficiency of LLMs with Self-Information-Based Content Filtering

Yucheng Li

Large language models (LLMs) have received significant attention by achieving remarkable performance across various tasks. However, their fixed context length poses challenges when…

cs.CL2023

Metaphor Detection with Effective Context Denoising

Shun Wang, Yucheng Li, Chenghua Lin +2

We propose a novel RoBERTa-based model, RoPPT, which introduces a target-oriented parse tree structure in metaphor detection. Compared to existing models, RoPPT focuses on semantic…