@HEI profile picture
Natural Language Processing Papers @HEI

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

Joined December 2010
  • Tweets 30,007
  • Following 5
  • Followers 1,796
4,957 Photos and videos
Adaptive Multi-Resolution Procedural Knowledge Compression for Large Language Models Changyue Wang, Weihang Su, Qingyao Ai, Yichen Tang, Runzhong Qiao, Xuancheng Li, Min Zhang, Yiqun Liu arxiv.org/abs/2606.12203 [𝚌𝚜.𝙲𝙻]

Adaptive Multi-Resolution Procedural Knowledge Compression for...

Large language models (LLMs) are widely used to tackle complex tasks with autonomous workflows. Recently, reusable natural language skills have emerged as a popular paradigm to inject procedural...

arxiv.org
12
Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application Jiachun Li, Zhuoran Jin, Tianyi Men, Yupu Hao, Kejian Zhu, Lingshuai Wang, Dongqi Huang, … arxiv.org/abs/2606.12191 [𝚌𝚜.𝙲𝙻 𝚌𝚜.𝙰𝙸]

Agentic Environment Engineering for Large Language Models: A...

Environments serve as interactive systems for large language model (LLM) based agents across diverse scenarios and play a crucial role in driving the continual evolution of model capabilities....

arxiv.org
23
A Resource for Enthymeme Detection in Controversial Political Discourse Martial Pastor, Nelleke Oostdijk arxiv.org/abs/2606.12186 [𝚌𝚜.𝙲𝙻] πŸ’¬Submitted to the Language Resource and Evaluation Journal

A Resource for Enthymeme Detection in Controversial Political Discourse

Enthymemes, arguments with unstated premises or conclusions, are pervasive in persuasive discourse, yet their annotation remains notoriously subjective. We present a resource of 1,482 tweets from...

arxiv.org
21
Soft-Prompt Tuning for Fair and Efficient LLM Benchmark Evaluation Selen Erkan, Bastian Boll, Kristian Kersting, BjΓΆrn Deiseroth, Letitia Parcalabescu arxiv.org/abs/2606.12117 [𝚌𝚜.𝙲𝙻 𝚌𝚜.𝙰𝙸]

Soft-Prompt Tuning for Fair and Efficient LLM Benchmark Evaluation

Benchmark scores often misrepresent a large language model's (LLM's) knowledge, because they rely, e.g., on the model's ability to follow specific formatting requirements. This especially...

arxiv.org
32
Detecting Sensitive Personal Information in Japanese Pre-Training Corpora for Large Language Models Rei Minamoto, Yusuke Oda, Daisuke Kawahara arxiv.org/abs/2606.12114 [𝚌𝚜.𝙲𝙻]

Detecting Sensitive Personal Information in Japanese Pre-Training...

Sensitive personal information can appear in large-scale pre-training corpora for large language models (LLMs). Detecting and filtering such information is therefore essential to ensure compliance...

arxiv.org
27
Augmenting Molecular Language Models with Local n-gram Memory Xinni Zhang, Zijing Liu, He Cao, Yu Li, Irwin King arxiv.org/abs/2606.12113 [𝚌𝚜.𝙲𝙻 𝚌𝚜.𝙰𝙸]

Augmenting Molecular Language Models with Local $n$-gram Memory

Transformer-based language models for SMILES strings suffer from a locality gap: standard character-level tokenization fragments chemically meaningful motifs, forcing models to repeatedly learn...

arxiv.org
40
Debiasing Without Protected Attributes: Latent Concept Erasure from Textual Profiles Shun Shao, Zheng Zhao, Anna Korhonen, Yftah Ziser, Shay B. Cohen arxiv.org/abs/2606.12088 [𝚌𝚜.𝙲𝙻]

Debiasing Without Protected Attributes: Latent Concept Erasure...

Most fairness research in NLP assumes direct access to protected attributes such as gender, race, or nationality. In practice, however, such information is often unavailable due to privacy...

arxiv.org
30
FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents Jia Deng, Yimeng Chen, Xiaoqing Xiang, Ziyang Zeng, Shuo Tang, Wayne Xin Zhao, Feng Chang, Chuan Hao, Yuan Wei, Ran Tao, Bryan Dai, Ji-Rong Wen arxiv.org/abs/2606.12087 [𝚌𝚜.𝙲𝙻]

FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for...

Training deep search agents requires verifiable questions whose answers remain unavailable until sufficient evidence has been acquired through search. Existing synthesis methods often increase...

arxiv.org
53
StanceNakba Shared Task: Actor and Topic-Aware Stance Detection in Public Discourse Kholoud K. Aldous, Md Rafiul Biswas, Mabrouka Bessghaier, Shimaa Ibrahim, Kais Attia, Wajdi Zaghouani arxiv.org/abs/2606.12068 [𝚌𝚜.𝙲𝙻]

StanceNakba Shared Task: Actor and Topic-Aware Stance Detection in...

We present StanceNakba 2026, a shared task on stance detection in polarized social media discourse related to the Palestinian-Israeli conflict, organized as part of Nakba-NLP 2026 at LREC-COLING...

arxiv.org
29
Agreement in Representation Space for Open-Ended Self-Consistency Paula Ontalvilla, Gorka Azkune, Aitor Ormazabal arxiv.org/abs/2606.12003 [𝚌𝚜.𝙲𝙻]

Agreement in Representation Space for Open-Ended Self-Consistency

Self-consistency improves LLM reasoning by sampling multiple outputs and selecting the most consistent answer, but existing formulations largely rely on exact matching and therefore remain limited...

arxiv.org
30
Decoding Multimodal Cues: Unveiling the Implicit Meaning Behind Hateful Videos Junyu Lu, Deyi Ji, Liqun Liu, Xiaokun Zhang, Youlin Wu, Roy Ka-Wei Lee, Peng Shu, Huan Yu, Jie Jiang, Bo Xu, Liang Yang, Hongfei Lin arxiv.org/abs/2606.11953 [𝚌𝚜.𝙲𝙻]

Decoding Multimodal Cues: Unveiling the Implicit Meaning Behind...

Hateful videos have become prevalent on online platforms, highlighting an urgent need for effective detection. However, existing studies primarily focus on binary classification and fail to...

arxiv.org
56
uva-irlab-conv at SemEval-2026 Task 8: Multi-Turn RAG with Learned Sparse Retrieval and Listwise Reranking Simon Lupart, Kidist Amde Mekonnen, Zahra Abbasiantaeb, Mohammad Aliannejadi arxiv.org/abs/2606.11945 [𝚌𝚜.𝙲𝙻 𝚌𝚜.π™Έπš]

uva-irlab-conv at SemEval-2026 Task 8: Multi-Turn RAG with Learned...

This report describes our participation in SemEval-2026 Task 8 on multi-turn retrieval and question answering. The task evaluates conversational systems across four domains (finance, cloud...

arxiv.org
27
Semantic Grading of Written Answers in Low-Resource Language Bangla Using a Fine-Tuned Lightweight Language Model Meherun Farzana, Aniket Joarder, Mahmudul Hasan, Md. Mosaddek Khan arxiv.org/abs/2606.11931 [𝚌𝚜.𝙲𝙻]

Semantic Grading of Written Answers in Low-Resource Language...

Bangla is among the world's most widely spoken languages, yet it remains underserved in educational NLP research. In many remote and rural regions, access to qualified subject teachers is limited,...

arxiv.org
28
Toward Generalist Autonomous Research via Hypothesis-Tree Refinement Jiajie Jin, Yuyang Hu, Kai Qiu, Qi Dai, Chong Luo, Guanting Dong, Xiaoxi Li, Tong Zhao, Xiaolong Ma, Gongrui Zhang, Zhirong Wu, Bei Liu, Zhengyuan Yang, … arxiv.org/abs/2606.11926 [𝚌𝚜.𝙲𝙻 𝚌𝚜.𝙰𝙸]

Toward Generalist Autonomous Research via Hypothesis-Tree Refinement

Scientific progress depends on a repeated loop of exploration, experimentation, and abstraction. Researchers test candidate directions, interpret the evidence, and carry the resulting lessons into...

arxiv.org
1
78
An Ontology-Guided Multi-Anchor Graph Retrieval Framework for Traffic Legal Liability Determination Xu Li, Shuqi Tian, Xun Han, Kuncheng Zhao, Xinyi Li arxiv.org/abs/2606.11910 [𝚌𝚜.𝙲𝙻] πŸ’¬Submitted to ICONIP

An Ontology-Guided Multi-Anchor Graph Retrieval Framework for...

Traffic law liability determination is critical for assigning legal penalties, requiring the simultaneous identification of interdependent statutory provisions across multiple legal dimensions....

arxiv.org
64
When Does Language Matter? Multilingual Instructions Reveal Step-wise Language Sensitivity in Vision-Language-Action Models Xuan Dong, Zhe Han, Tianhao Niu, Qingfu Zhu, Wanxiang Che arxiv.org/abs/2606.11906 [𝚌𝚜.𝙲𝙻] πŸ’¬Accepted to ACL 2026 Main Conference

When Does Language Matter? Multilingual Instructions Reveal...

Vision-Language-Action (VLA) models have shown strong performance in language-conditioned robotic manipulation, yet their robustness to linguistic variation remains poorly understood. In this...

arxiv.org
44
Notes2Skills: From Lab Notebooks to Certainty-Aware Scientific Agent Skills Shi Liu, Jiayao Chen, Chengwei Qin, Yanqing Hu, Jufan Zhang, Linyi Yang arxiv.org/abs/2606.11897 [𝚌𝚜.𝙲𝙻]

Notes2Skills: From Lab Notebooks to Certainty-Aware Scientific Agent Skills

Scientific discovery workflows usually contain and rely heavily on lab notes, where researchers record observations, interpret uncertain results, and plan follow-up experiments. Such informative...

arxiv.org
1
61
I Understand How You Feel: Enhancing Deeper Emotional Support Through Multilingual Emotional Validation in Dialogue System Zi Haur Pang, Yahui Fu, Koji Inoue, Tatsuya Kawahara arxiv.org/abs/2606.11875 [𝚌𝚜.𝙲𝙻 𝚌𝚜.πš‚π™³]

I Understand How You Feel: Enhancing Deeper Emotional Support...

Emotional validation - explicitly acknowledging that a user's feelings make sense - has proven therapeutic value but has received little computational attention. Emotional validation in dialogue...

arxiv.org
39
WorldReasoner: Evaluating Whether Language Model Agents Forecast Events with Valid Reasoning Yizhou Chi, Eric Chamoun, Zifeng Ding, Andreas Vlachos arxiv.org/abs/2606.11816 [𝚌𝚜.𝙲𝙻 𝚌𝚜.𝙰𝙸]

WorldReasoner: Evaluating Whether Language Model Agents Forecast...

Forecasting real-world events requires language-model agents to reason under uncertainty from incomplete, time-bounded information. Yet evaluating whether agents genuinely forecast requires more...

arxiv.org
46
External Experience Serving in Production LLM Systems: A Deployment-Oriented Study of Quality-Cost Trade-offs Lin Sun, Heming Zhang, Xiangzheng Zhang arxiv.org/abs/2606.11806 [𝚌𝚜.𝙲𝙻]

External Experience Serving in Production LLM Systems: A...

Production LLM systems accumulate reusable operational experience, but the practical deployment issue is not merely whether such experience can help. It is how different serving strategies trade...

arxiv.org
1
57
Load more