cs.CL · 2026-09-28 · No. 127
Computation and Language, 2026-09-28.
10 new papers in cs.CL. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
10 entries-
01
Evaluating Cultural Awareness of LLMs for Haitian Creole
Christelle Clervilsson, Yanzhu Guo
cs.CL · cs.AI
Large language models (LLMs) exhibit substantial performance disparities between high- and low-resource languages. Beyond lower task performance, they often fail to capture the cultural norms and values of underrepresented communities. In this work, we present the first systematic evaluation of cultural awareness in LLMs for Haitian Creole, a language spoken by millions but severely underrepresented in digital resources. We assess cultural...
-
02
ViSTA: A Simple Bridge Extends Visual Alignment to Clinical Time-Series Understanding in Multimodal LLMs
Junyi Gao, Yu Shi, Pingzhao Hu, Ewen M Harrison
cs.CL · cs.AI
Clinical prediction models estimate risk from patient measurements, while large language models support medical text understanding and question answering. Yet their language capabilities do not ensure accurate prediction from structured, high-dimensional clinical time series. Improving this ability would connect risk estimation with flexible questions about a patient's evolving condition. We introduce ViSTA, a compact adapter that...
-
03
Sorry Robot, Happy Human: Vision-Language Models Read Only One of Two Legible Typographic Layers
Mert İncidelen, Yamen Kashkash, Asya Berker, Murat Aydoğan
cs.CL · cs.AI · cs.CV
Vision-language models (VLMs), despite their success in optical character recognition (OCR) tasks, are vulnerable to typographic attacks and have a fragile structure for images with multiple text layers. In this study, the DecoyBench dataset was created using the Decoy Font method. The dataset consists of 300 images, each containing text with sharp contour lines superimposed on another text with soft shading. Six recent closed-source models...
-
04
Highlight-Then-Summarize: Learning to Compress Evidence for Long-Context Understanding
Zhaoyuan Xia, Qinghongbing Xie, Yung Xiang Hue, Jianguang Jiang, Gaofeng Lu, Zhenyu Jiao, Xing Yuan, Dai Dai, Tong...
cs.CL · cs.AI
Long-context understanding requires large language models (LLMs) to reason over lengthy documents, conversations, and code, yet task-relevant evidence is often sparse and scattered amid substantial irrelevant and redundant content. We propose Highlight-Then-Summarize (H2S), a compress-then-reason paradigm that first identifies source-grounded, question-relevant evidence and then integrates it into a compact, question-conditioned summary...
-
05
MoSAR: Mixture of Semantic Attention Regimes for Learning Adaptive and Approximable Attention Geometries
Michele Paolicelli, Alessandro Petruzzelli, Alessandro Franceso Maria Martina, Cataldo Musto, Giovanni Semeraro
cs.CL · cs.AI
The quadratic complexity of dense self-attention remains a central bottleneck for long-context language modeling. Many efficient alternatives address this cost by deciding in advance where attention should be sparse or local. We argue that attention approximation should instead be approached as a geometric problem, with the relevant interaction geometry learned from data: natural-language dependencies are input-dependent and difficult to...
-
06
Improving Visual Sensitivity of LLMs on Multimodal Machine Translation with Metric-based Loss Weighting
Paweł Mąka, Piotr Andruszkiewicz, Yusuf Can Semerci, Jan Scholtes, Gerasimos Spanakis
cs.CL · cs.AI
Multimodal Machine Translation aims to incorporate additional signal from non-textual modalities to improve translations by resolving ambiguities. While models, through multimodal fusion, are able to accept images related to the source text, they can ignore this information. Therefore, increasing their visual sensitivity remains an active research area. In this work, we introduce a training method, Metric-based Loss Weighting, that improves...
-
07
LocUS: Head Selection and Subspace Projection for Targeted Activation Steering
Irene Tallini, Lorenzo Basile, Valentino Maiorca, Francesco Locatello, Alberto Cazzaniga
cs.CL · cs.LG
Activation steering is a powerful training-free paradigm for controlling large language models at inference time. However, standard approaches estimate a per-layer steering direction from contrastive data and apply it on the layer's entire representation space, which may couple the intervention to off-target properties present in the contrastive data and degrade unrelated capabilities. To mitigate this issue, we introduce LocUS (Localized...
-
08
G$^2$PTQ: Improving LLM Post-Training Quantization with Generalized Gradient Compensation
Ruikang Liu, Haoli Bai, Yuxuan Sun, Qian Zhang, Wenzheng Cai, Yanqi Hao, Feiyu Wang, Weidong Zhong, Zhuang Wang,...
cs.CL · cs.AI
Post-training quantization (PTQ) is a practical approach to reducing the memory and computational footprint of large language models (LLMs) without retraining. GPTQ-based methods have become the de facto standard, yet they suffer from two complementary limitations. Methods with local, layer-wise objectives lack global supervision; while methods with global objectives fix their Hessian estimates at the start and ignore first-order gradients,...
-
09
Estimating and Orthogonalizing Unknown Pre-training Gradients for Continual Fine-tuning of Large Language Models
Bing Wang, Changchun Li, Xin-Qiang Cai, Lin Yuanbo Wu, Ximing Li, Gang Niu, Masashi Sugiyama
cs.CL · cs.AI · cs.LG
Continual fine-tuning is essential for large language models (LLMs) to dynamically adapt to real-world environments, yet it inevitably suffers from catastrophic forgetting, particularly the performance degradation of previous tasks and LLMs' general-purpose knowledge. Although existing methods, such as orthogonal gradient projection, mitigate the forgetting across various fine-tuning tasks, they fundamentally fail to preserve pre-training...
-
10
Persistent Negatives for Adversarial Black-Box On-Policy Distillation
Haixu Ma, Saad Lahrichi, Weiwei Li, Kevin Han, Weiqiang Wu, Peggy Yang, Dongzhuo Li, Ruiyi Li, Serena Li, Gedi Zhou,...
cs.CL · cs.AI
Black-box On-Policy Distillation (OPD) seeks to improve a student from its own generations when the teacher provides sampled responses but not token probabilities. Adversarial distillation offers one route: it learns a discriminator over prompt-matched teacher and student responses and uses its score as the policy reward. However, sampling discriminator negatives from the latest student at each step couples the learned reward to a negative...
This edition is part of The Daily Abstract — cs.CL archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.