Papers with information quality
Thesis Proposal: Comparing Human and Model Perception of Writing Style under Controlled Perturbations (2026.eacl-srw)
Copied to clipboard
| Challenge: | This thesis examines how humans and models perceive writing style under controlled perturbations. |
| Approach: | They examine how humans and models perceive writing style under controlled perturbations . they also examine whether perturbations that reduce algorithmic recognition obscure stylistic identity . |
| Outcome: | The proposed research compares models and humans to find out how linguistic cues affect writing style . it will clarify how linguistic cue contributes differently to human and algorithmic perception of style - a cnn.com article argues . |
Not All Directions Matter: Towards Structured and Task-Aware Low-Rank Model Adaptation (2026.acl-long)
Copied to clipboard
Xi Xiao, Chenrui Ma, Yunbei Zhang, Chen Liu, Zhuxuanzi Wang, Yanshu Li, Lin Zhao, Guosheng Hu, Tianyang Wang, Hao Xu
| Challenge: | Low-Rank Adaptation (LoRA) is a key parameter-efficient fine-tuning method . however, its effectiveness is hampered by semantic drift and structural incoherence . |
| Approach: | They propose a low-rank Adaptation framework that tackles semantic drift and structural incoherence by pruning task-irrelevant directions. |
| Outcome: | Experiments on large language models, vision models, and vision models show that the proposed framework outperforms LoRA and advanced dynamic rank allocation and sparsity-based methods. |
Modeling Bottom-up Information Quality during Language Processing (2025.emnlp-main)
Copied to clipboard
| Challenge: | Contemporary theories of language processing model language processing as integrating both top-down expectations and bottom-up inputs. |
| Approach: | They propose an information-theoretic operationalization for the “quality” of bottom-up information as the mutual information between visual information and word identity. |
| Outcome: | The proposed model compares reading times in English and Chinese in which words' information quality has been reduced by occluding their top or bottom half with full words. |