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]

Implicit Geographic Inference in LLM Medical Triage: Language-Driven Disparities in Emergency Recommendations

Qi Han Wong
https://t.co/hKxVVxMlRG [𝚌𝚜.𝙲𝙻 𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙲𝚈]
💬Code: https://t.co/VE3KiDHLQG

[Natural Language Processing Papers @HEI]

Low-Resource Safety Failures Are Action Failures, Not Representation Failures

Rashad Aziz, Ikhlasul Akmal Hanif, Fajri Koto
https://t.co/rKY8Lw1ucI [𝚌𝚜.𝙲𝙻 𝚌𝚜.𝙰𝙸]

[Natural Language Processing Papers @HEI]

CA-BED: Conversation-Aware Bayesian Experimental Design

Daniel Arnould, Rashad Aziz, Zixuan Kang, Tanav Changal, Kevin Zhu, Sunishchal Dev, Gabriel Grand, Shreyas Sunil Kulkarni
https://t.co/AzVRf7WZv2 [𝚌𝚜.𝙲𝙻 𝚌𝚜.𝙰𝙸]
💬Reliable Autonomy Workshop at ICLR 2026

[Natural Language Processing Papers @HEI]

Thinking Economically: A Hierarchical Framework for Adaptive-Complexity Reasoning in LLMs

Yubo Gao, Haotian Wu, Hong Chen, Junquan Huang, Yibo Yan, Jungang Li, Zihao Dongfang, Sicheng Tao, Puay Siew Tan, Jie Zhang, Xuming Hu
https://t.co/DkhO7GZu1T [𝚌𝚜.𝙲𝙻]

[Natural Language Processing Papers @HEI]

Not All Explanations Simulate Equally: Comparing Verbalized Feature Attributions and Self-Generated Rationales

Pingjun Hong, Benjamin Roth
https://t.co/SdfiqG4lxg [𝚌𝚜.𝙲𝙻]

[Natural Language Processing Papers @HEI]

From Outliers to Errors: Auditing Pali-to-English LLM Translations with Multi-Reference Adjudication

Máté Metzger, Nadnapang Phophichit, Hansa Dhammahaso
https://t.co/u2iYDkrOci [𝚌𝚜.𝙲𝙻]

[Natural Language Processing Papers @HEI]

MiCU: End-to-End Smart Home Command Understanding with Large Language Model

Haowei Han, Kexin Hu, Weiwei Cai, Debiao Zhang, Bin Qin, Yuxiang Wang, Jiawei Jiang, Xiao Yan, Bo Du
https://t.co/VvChQ5FNHd [𝚌𝚜.𝙲𝙻 𝚌𝚜.𝙰𝙸]

[Natural Language Processing Papers @HEI]

Deep Research as Rubric for Reinforcement Learning

Wangyi Mei, Zhouhong Gu, Zhenhan Bai, Yin Cai, Lefan Zhang, Zhenxin Ding, Bo Chen, Yan Gao, Yi Wu, Yao Hu, Jiaqing Liang, Deqing Yang
https://t.co/MTxulO2ytX [𝚌𝚜.𝙲𝙻]

[Natural Language Processing Papers @HEI]

On the Generalization Gap in Self-Evolving Language Model Reasoning

Zhenting Qi, Susanna Maria Baby, Stefanie Anna Baby, Kan Yuan, Andrew Tomkins, Tu Vu, Da-Cheng Juan, Cyrus Rashtchian
https://t.co/de0n8HfvR8 [𝚌𝚜.𝙲𝙻]

[Natural Language Processing Papers @HEI]

When Is 0.1% Enough? Analyzing the Combined Effects of Dimensionality Reduction and Quantization on Text Embedding Compression

Riku Kisako, Hayato Tsukagoshi, Ryohei Sasano
https://t.co/N20g6gvleV [𝚌𝚜.𝙲𝙻]

[Natural Language Processing Papers @HEI]

MENTIS: What Belief Changes Under Alignment? Measuring Multi-Scale Latent Torsion in Language Models

Partha Pratim Saha, Samarth Raina, Mayur Parvatikar, Amit Dhanda, Vinija Jain, Aman Chadha, …
https://t.co/9Pja6Q0q5a [𝚌𝚜.𝙲𝙻 𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙻𝙶]
💬Submitted to EMNLP 2026

[Natural Language Processing Papers @HEI]

PMC-InterCPT: Rethinking Biomedical Interleaved Data for Multimodal Continued Pretraining

Guanghao Zhu, Zeyu Liu, Zhitian Hou, Pengkai Wang, Zhijie Sang, Minheng Ni, Wenjun Wang, Yanggan Gu, Shuo Cai, Congkai Xie, Jianmin Wu, Hongxia Yang
https://t.co/T0z7d1bHMj [𝚌𝚜.𝙲𝙻]

[Natural Language Processing Papers @HEI]

Child-directed speech facilitates production, not comprehension, in BabyLMs

Bastian Bunzeck, Sina Zarrieß
https://t.co/DszQm1I5HK [𝚌𝚜.𝙲𝙻]
💬Accepted at CoNLL 2026

[Natural Language Processing Papers @HEI]

ExpWeaver: LLM Agents Learn from Experience via Latent RAG

Tao Feng, Tianyang Luo, Jingjun Xu, Zhigang Hua, Yan Xie, Shuang Yang, Ge Liu, Jiaxuan You
https://t.co/5QUIJpDYbU [𝚌𝚜.𝙲𝙻]

[Natural Language Processing Papers @HEI]

A Finite-Calibration Regime Map for LLM Judge Panels

Bin Zhu, Yanghui Rao
https://t.co/kvwkqqJOn1 [𝚌𝚜.𝙲𝙻 𝚜𝚝𝚊𝚝.𝙼𝙴]

[Natural Language Processing Papers @HEI]

Revise, Don't Freeze: Sampler-Matched Training for Self-Correcting Masked Diffusion Language Models

Longxuan Yu, Shaorong Zhang, Yu Fu, Hui Liu, Yue Dong, Greg Ver Steeg
https://t.co/GyeF1ncAA4 [𝚌𝚜.𝙲𝙻]

[Natural Language Processing Papers @HEI]

DSL-LLaDA: Scaling Continuous Denoising to 8B Masked Diffusion LMs

Longxuan Yu, Yunshu Wu, Yu Fu, Siheng Xiong, Rob Brekelmans, Hui Liu, Yue Dong, Greg Ver Steeg
https://t.co/xnnY76KOBd [𝚌𝚜.𝙲𝙻 𝚌𝚜.𝙰𝙸]

[Natural Language Processing Papers @HEI]

Hybrid Verified Decoding: Learning to Allocate Verification in Speculative Decoding

Xin Su, Dawid Majchrowski, Fangyuan Yu, Vanshil Atul Shah, Sebastian Rogawski, Pawel Morkisz, Anahita Bhiwandiwalla, Phillip Howard
https://t.co/Yl8boK7pkJ [𝚌𝚜.𝙲𝙻 𝚌𝚜.𝙰𝙸]

[Natural Language Processing Papers @HEI]

PolySpeech-100: A Large-Scale Benchmark for Speech Understanding Across 100+ Languages and Dialects

Sicheng Yang, Shulan Ruan, Shiwei Wu, Yu Liu, Lu Fan, Zhi Li, You He
https://t.co/NEkHzXN8a3 [𝚌𝚜.𝙲𝙻 𝚌𝚜.𝙰𝙸 𝚎𝚎𝚜𝚜.𝙰𝚂]

[Natural Language Processing Papers @HEI]

Decoding in Order-Agnostic Language Models: Chain-Rule Deviation and Uniform Spreading

Lin Yao
https://t.co/bFH9KyFCqO [𝚌𝚜.𝙲𝙻]