Natural Language Processing Papers

New Natural Language Processing papers from natural language processing. Thank you to arXiv for use of its open access interoperability.

[Natural Language Processing Papers @HEI]

How Many Labels Does a Language Need? Annotation Budgets and Cross-Lingual Pooling for African-Language Text Classification

Bhanu Prakash Vangala, Sowmya Guda, Navya Vangala
https://t.co/fL5D44Tyo7 [𝚌𝚜.𝙲𝙻 𝚌𝚜.𝙻𝙶]

[Natural Language Processing Papers @HEI]

Retrieval Capacity of Self-Attention Under Competition

Timur Mudarisov, Mikhail Burtsev, Radu State
https://t.co/zdwkx8ECAv [𝚌𝚜.𝙲𝙻 𝚌𝚜.𝙻𝙶]

[Natural Language Processing Papers @HEI]

It's Not What the Image Shows: Irrelevant Context Destabilises VLM Judges Without Informing Them

Nagham Omar, Mahmoud Jabarin, Kinan Ibraheem, Lotem Peled-Cohen
https://t.co/qp5osGp6HE [𝚌𝚜.𝙲𝙻 𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙲𝚅]
💬Accepted at TAE (Trust-AI-Eval) @ NeurIPS 2026

[Natural Language Processing Papers @HEI]

One Threshold Does Not Fit All Languages: Language-Conditional Deferral for Reliable and Efficient Low-Resource Text Classification

Bhanu Prakash Vangala, Vangala Navya
https://t.co/0jhVxtReiN [𝚌𝚜.𝙲𝙻 𝚌𝚜.𝙻𝙶]

[Natural Language Processing Papers @HEI]

AnthroDial: Benchmarking LLM Anthropomorphism in Autonomous Social Interaction

Wentao Liu, Xi Chen, Siyu Song, Biao Yuan, Yu Zhang, Zhou Zhuotong, Jingying Zhou, Guohao Feng, Shasha Hu, Tianfu Wang, Shangshang Yang, Haoyang Liu, Youjia Li, …
https://t.co/lLa4bxlyT5 [𝚌𝚜.𝙲𝙻]

[Natural Language Processing Papers @HEI]

Can Vision-Language Models Stay Helpful When Facing Implicit Risks? Intent-Privilege OPSD for Efficient Safety-Helpfulness Alignment

Haotian Deng, Wenbin Xing, Gang Xu, Tao He, Jinkai Zheng, Chun Li, Zheng Zhu, Ming Li
https://t.co/rqw7cVZmnL [𝚌𝚜.𝙲𝙻]

[Natural Language Processing Papers @HEI]

The Geometry of Inference in Transformer Residual Streams

Timur Mudarisov, Mikhail Burtsev, Radu State
https://t.co/dT4bvthtwC [𝚌𝚜.𝙲𝙻 𝚌𝚜.𝙻𝙶]

[Natural Language Processing Papers @HEI]

Thinking in Depth, Speaking Directly: Recurrent Latent Reasoning for Paralinguistically Grounded Spoken Dialogue

Shengbo Cai, Yuxiang Wang, Jingran Xie, Zhisheng Zhang, Shun Lei, Di Cao, Teddy Sun, Zhiyong Wu
https://t.co/PkN8nTVgFZ [𝚌𝚜.𝙲𝙻 𝚌𝚜.𝙰𝙸]

[Natural Language Processing Papers @HEI]

CompOrca: Corpus-Scale Compliance Labelling of Instruction-Tuning Data

Philipp E. Glass, Alina Miron
https://t.co/QeT7QEt3Ox [𝚌𝚜.𝙲𝙻 𝚌𝚜.𝙻𝙶]
💬Accepted to PlurVA-LLM Workshop @ AACL-IJCNLP 2026

[Natural Language Processing Papers @HEI]

A Proposed Rubric for Evaluating Expressed Clinical Reasoning in Large Language Model Responses

Zhangshu Joshua Jiang, Zina Ibrahim, James T. Teo
https://t.co/5wLeDDICOX [𝚌𝚜.𝙲𝙻 𝚌𝚜.𝙰𝙸]

[Natural Language Processing Papers @HEI]

Selecting What Matters: Semantic Compression-Guided Selective Pooling for Long-Context Embeddings

Zifeng Cheng, Jie Zheng, Zhiwei Jiang, Shuwen Wang, Fei Shen, Shiping Ge, Qing Gu
https://t.co/1yhdL6WuvJ [𝚌𝚜.𝙲𝙻]

[Natural Language Processing Papers @HEI]

Which papyrus HTR is good enough? Character-error-rate tolerance of four papyrological tasks on Greek texts

Anton Repushko, Elena Chepel
https://t.co/TjkR1Wjkax [𝚌𝚜.𝙲𝙻]

[Natural Language Processing Papers @HEI]

https://t.co/RVzUBLfzkx Products: A Bilingual Entity Matching Benchmark

Aaron Steiner, Ksenia Elagin, Ralph Peeters, Johannes Knopp, Christian Bizer
https://t.co/GWSNLWtW7h [𝚌𝚜.𝙲𝙻]
💬Code: https://t.co/kOVboWw91m

[Natural Language Processing Papers @HEI]

Reader Proficiency Shapes Layer-wise Surprisal Profiles

Akio Hayakawa, Horacio Saggion
https://t.co/o09ervsKUW [𝚌𝚜.𝙲𝙻]

[Natural Language Processing Papers @HEI]

Corpus-Guided Dual-Path Propagation for Graph Retrieval-Augmented Generation

Baoxian Liu, Tong Wei
https://t.co/863T6B2CCv [𝚌𝚜.𝙲𝙻]

[Natural Language Processing Papers @HEI]

Evaluating and Benchmarking the System One Model Jev

Tobias Deußer, Lorenz Sparrenberg, Rafet Sifa
https://t.co/xyTyhdqacQ [𝚌𝚜.𝙲𝙻 𝚌𝚜.𝙰𝙸]

[Natural Language Processing Papers @HEI]

Co-Linguistics: AI-augmented Theory Construction in Linguistics

Emmanuel Chemla, Benjamin Spector, Alexandros Kalomoiros, Philippe Schlenker
https://t.co/S3zc78MQSE [𝚌𝚜.𝙲𝙻]

[Natural Language Processing Papers @HEI]

Correct, Don't Delete: Mitigating Emergent Misalignment with Corrective Supervision

Jacob Epifano
https://t.co/XKmVnOsu41 [𝚌𝚜.𝙲𝙻 𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙻𝙶]

[Natural Language Processing Papers @HEI]

Pair Difficulty Matters: Rethinking Pairwise LLM-as-a-Judge Evaluation and Consistency

Bruno Brocai, Maria Becker
https://t.co/AfVJdtUJ9E [𝚌𝚜.𝙲𝙻]

[Natural Language Processing Papers @HEI]

Devils in Question Relay: Source-Conditioned Relay Steering to Mitigate Hallucinations in Audio-visual Large Language Models

Yu Zhang, Pingrui Zhang, Xuefeng Bai, Pengfei Zhang, Yang Xiang, Kehai Chen
https://t.co/xUF2l9SHaw [𝚌𝚜.𝙲𝙻]