Academic

Academic · 1 min

Unveiling Language Routing Isolation in Multilingual MoE Models for Interpretable Subnetwork Adaptation

arXiv:2604.03592v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models exhibit striking performance disparities across languages, yet the internal mechanisms driving these gaps remain poorly understood. In …

Kening Zheng, Wei-Chieh Huang, Jiahao Huo, Zhonghao Li, Henry Peng Zou, Yibo Yan, Xin Zou, Jungang Li, Junzhuo Li, Hanrong Zhang, Xuming Hu, Philip S. Yu

4 views Apr 7

Academic · 1 min

MultiPress: A Multi-Agent Framework for Interpretable Multimodal News Classification

arXiv:2604.03586v1 Announce Type: new Abstract: With the growing prevalence of multimodal news content, effective news topic classification demands models capable of jointly understanding and reasoning …

Tailong Luo, Hao Li, Rong Fu, Xinyue Jiang, Huaxuan Ding, Yiduo Zhang, Zilin Zhao, Simon Fong, Guangyin Jin, Jianyuan Ni

5 views Apr 7

Academic · 1 min

Text Summarization With Graph Attention Networks

arXiv:2604.03583v1 Announce Type: new Abstract: This study aimed to leverage graph information, particularly Rhetorical Structure Theory (RST) and Co-reference (Coref) graphs, to enhance the performance …

Mohammadreza Ardestani, Yllias Chali

9 views Apr 7

Academic · 1 min

Rethinking Token Prediction: Tree-Structured Diffusion Language Model

arXiv:2604.03537v1 Announce Type: new Abstract: Discrete diffusion language models have emerged as a competitive alternative to auto-regressive language models, but training them efficiently under limited …

Zihao Wu, Haoming Yang, Juncheng Dong, Vahid Tarokh

4 views Apr 7

Academic · 1 min

LangFIR: Discovering Sparse Language-Specific Features from Monolingual Data for Language Steering

arXiv:2604.03532v1 Announce Type: new Abstract: Large language models (LLMs) show strong multilingual capabilities, yet reliably controlling the language of their outputs remains difficult. Representation-level steering …

Sing Hieng Wong, Hassan Sajjad, A. B. Siddique

9 views Apr 7

Academic · 1 min

Cultural Authenticity: Comparing LLM Cultural Representations to Native Human Expectations

arXiv:2604.03493v1 Announce Type: new Abstract: Cultural representation in Large Language Model (LLM) outputs has primarily been evaluated through the proxies of cultural diversity and factual …

Erin MacMurray van Liemt, Aida Davani, Sinchana Kumbale, Neha Dixit, Sunipa Dev

4 views Apr 7

Academic · 1 min

Evolutionary Search for Automated Design of Uncertainty Quantification Methods

arXiv:2604.03473v1 Announce Type: new Abstract: Uncertainty quantification (UQ) methods for large language models are predominantly designed by hand based on domain knowledge and heuristics, limiting …

Mikhail Seleznyov, Daniil Korbut, Viktor Moskvoretskii, Oleg Somov, Alexander Panchenko, Elena Tutubalina

4 views Apr 7

Academic · 1 min

Vocabulary Dropout for Curriculum Diversity in LLM Co-Evolution

arXiv:2604.03472v1 Announce Type: new Abstract: Co-evolutionary self-play, where one language model generates problems and another solves them, promises autonomous curriculum learning without human supervision. In …

Jacob Dineen, Aswin RRV, Zhikun Xu, Ben Zhou

9 views Apr 7

Academic · 1 min

The Tool Illusion: Rethinking Tool Use in Web Agents

arXiv:2604.03465v1 Announce Type: new Abstract: As web agents rapidly evolve, an increasing body of work has moved beyond conventional atomic browser interactions and explored tool …

Renze Lou, Baolin Peng, Wenlin Yao, Qianhui Wu, Hao Cheng, Suman Nath, Wenpeng Yin, Jianfeng Gao

3 views Apr 7

Academic · 1 min

Towards a theory of morphology-driven marking in the lexicon: The case of the state

arXiv:2604.03422v1 Announce Type: new Abstract: All languages have a noun category, but its realisation varies considerably. Depending on the language, semantic and/or morphosyntactic differences may …

Mohamed El Idrissi

8 views Apr 7

Academic · 1 min

Are Arabic Benchmarks Reliable? QIMMA's Quality-First Approach to LLM Evaluation

arXiv:2604.03395v1 Announce Type: new Abstract: We present QIMMA, a quality-assured Arabic LLM leaderboard that places systematic benchmark validation at its core. Rather than aggregating existing …

Leen AlQadi, Ahmed Alzubaidi, Mohammed Alyafeai, Hamza Alobeidli, Maitha Alhammadi, Shaikha Alsuwaidi, Omar Alkaabi, Basma El Amel Boussaha, Hakim Hacid

6 views Apr 7

Academic · 1 min

Noise Steering for Controlled Text Generation: Improving Diversity and Reading-Level Fidelity in Arabic Educational Story …

arXiv:2604.03380v1 Announce Type: new Abstract: Generating diverse, pedagogically valid stories for Arabic early-grade reading assessments requires balancing tight constraints on vocabulary, reading level, and narrative …

Haziq Mohammad Khalid, Salsabeel Shapsough, Imran Zualkernan

3 views Apr 7

Unveiling Language Routing Isolation in Multilingual MoE Models for Interpretable Subnetwork Adaptation

MultiPress: A Multi-Agent Framework for Interpretable Multimodal News Classification

Text Summarization With Graph Attention Networks

Rethinking Token Prediction: Tree-Structured Diffusion Language Model

LangFIR: Discovering Sparse Language-Specific Features from Monolingual Data for Language Steering

Cultural Authenticity: Comparing LLM Cultural Representations to Native Human Expectations

Evolutionary Search for Automated Design of Uncertainty Quantification Methods

Vocabulary Dropout for Curriculum Diversity in LLM Co-Evolution

The Tool Illusion: Rethinking Tool Use in Web Agents

Towards a theory of morphology-driven marking in the lexicon: The case of the state

Are Arabic Benchmarks Reliable? QIMMA's Quality-First Approach to LLM Evaluation

Noise Steering for Controlled Text Generation: Improving Diversity and Reading-Level Fidelity in Arabic Educational Story …

JCG, PC

HSOLLC Co., Ltd.