NLP | KOINEU

NLP Data Computer Science

Surprisal and Metaphor Novelty Judgments: Moderate Correlations and Divergent Scaling Effects Revealed by Corpus-Based and Synthetic Datasets

📝 Original Info Title: Surprisal and Metaphor Novelty Judgments: Moderate Correlations and Divergent Scaling Effects Revealed by Corpus-Based and Synthetic Datasets ArXiv ID: 2601.02015 Date: 2026-01-05 Authors: Omar Momen, Emilie Sitter, Berenike …

January 05, 2026

Bridging the Data Gap: Creating a Hindi Text Summarization Dataset from the English XSUM

📝 Original Info Title: Bridging the Data Gap: Creating a Hindi Text Summarization Dataset from the English XSUM ArXiv ID: 2601.01543 Date: 2026-01-04 Authors: Praveenkumar Katwe, RakeshChandra Balabantaray, Kaliprasad Vittala 📝 Abstract 📄 Full …

January 04, 2026

NLP Data Computer Science

Lying with Truths: Open-Channel Multi-Agent Collusion for Belief Manipulation via Generative Montage

📝 Original Info Title: Lying with Truths: Open-Channel Multi-Agent Collusion for Belief Manipulation via Generative Montage ArXiv ID: 2601.01685 Date: 2026-01-04 Authors: Jinwei Hu, Xinmiao Huang, Youcheng Sun, Yi Dong, Xiaowei Huang 📝 Abstract As …

January 04, 2026

Does Memory Need Graphs? A Unified Framework and Empirical Analysis for Long-Term Dialog Memory

📝 Original Info Title: Does Memory Need Graphs? A Unified Framework and Empirical Analysis for Long-Term Dialog Memory ArXiv ID: 2601.01280 Date: 2026-01-03 Authors: Sen Hu, Yuxiang Wei, Jiaxin Ran, Zhiyuan Yao, Xueran Han, Huacan Wang, Ronghao Chen, …

NLP Framework Analysis Computer Science

From Policy to Logic for Efficient and Interpretable Coverage Assessment

📝 Original Info Title: From Policy to Logic for Efficient and Interpretable Coverage Assessment ArXiv ID: 2601.01266 Date: 2026-01-03 Authors: Rhitabrat Pokharel, Hamid Reza Hassanzadeh, Ameeta Agrawal 📝 Abstract Large Language Models (LLMs) have …

Intention Collapse: Intention-Level Metrics for Reasoning in Language Models

📝 Original Info Title: Intention Collapse: Intention-Level Metrics for Reasoning in Language Models ArXiv ID: 2601.01011 Date: 2026-01-03 Authors: Patricio Vera 📝 Abstract Language generation maps a rich, high-dimensional internal state to a single …

ks-lit-3m: A 3.1 million word kashmiri text dataset for large language model pretraining

📝 Original Info Title: ks-lit-3m: A 3.1 million word kashmiri text dataset for large language model pretraining ArXiv ID: 2601.01091 Date: 2026-01-03 Authors: Haq Nawaz Malik 📝 Abstract Large Language Models (LLMs) demonstrate remarkable fluency …

NLP Data Computer Science Model

Stylometry Analysis of Human and Machine Text for Academic Integrity

📝 Original Info Title: Stylometry Analysis of Human and Machine Text for Academic Integrity ArXiv ID: 2601.01225 Date: 2026-01-03 Authors: Hezam Albaqami, Muhammad Asif Ayub, Nasir Ahmad, Yaseen Ahmad, Mohammed M. Alqahtani, Abdullah M. Algamdi, …

NLP Analysis Computer Science

T3C: Test-Time Tensor Compression with Consistency Guarantees

📝 Original Info Title: T3C: Test-Time Tensor Compression with Consistency Guarantees ArXiv ID: 2601.01299 Date: 2026-01-03 Authors: Ismail Lamaakal, Chaymae Yahyati, Yassine Maleh, Khalid El Makkaoui, Ibrahim Ouahbi 📝 Abstract We present T3C, a …

ECR: Manifold-Guided Semantic Cues for Compact Language Models

📝 Original Info Title: ECR: Manifold-Guided Semantic Cues for Compact Language Models ArXiv ID: 2601.00543 Date: 2026-01-02 Authors: Chung-Wei Victor Yuan 📝 Abstract Compact models often lose the structure of their embedding space. The issue shows up …

January 02, 2026

Beyond Perfect APIs: A Comprehensive Evaluation of LLM Agents Under Real-World API Complexity

📝 Original Info Title: Beyond Perfect APIs: A Comprehensive Evaluation of LLM Agents Under Real-World API Complexity ArXiv ID: 2601.00268 Date: 2026-01-01 Authors: Doyoung Kim, Zhiwei Ren, Jie Hao, Zhongkai Sun, Lichao Wang, Xiyao Ma, Zack Ye, Xu …

January 01, 2026

NLP Data Computer Science

Do LLMs Judge Distantly Supervised Named Entity Labels Well? Constructing the JudgeWEL Dataset

📝 Original Info Title: Do LLMs Judge Distantly Supervised Named Entity Labels Well? Constructing the JudgeWEL Dataset ArXiv ID: 2601.00411 Date: 2026-01-01 Authors: Alistair Plum, Laura Bernardy, Tharindu Ranasinghe 📝 Abstract We present judgeWEL, a …

January 01, 2026

AdaGReS:Adaptive Greedy Context Selection via Redundancy-Aware Scoring for Token-Budgeted RAG

📝 Original Info Title: AdaGReS:Adaptive Greedy Context Selection via Redundancy-Aware Scoring for Token-Budgeted RAG ArXiv ID: 2512.25052 Date: 2025-12-31 Authors: Chao Peng, Bin Wang, Zhilei Long, Jinfang Sheng 📝 Abstract Retrieval-augmented …

Big AI is accelerating the metacrisis: What can we do?

📝 Original Info Title: Big AI is accelerating the metacrisis: What can we do? ArXiv ID: 2512.24863 Date: 2025-12-31 Authors: Steven Bird 📝 Abstract The world is in the grip of ecological, meaning, and language crises which are converging into a …

Encyclo-K: Evaluating LLMs with Dynamically Composed Knowledge Statements

📝 Original Info Title: Encyclo-K: Evaluating LLMs with Dynamically Composed Knowledge Statements ArXiv ID: 2512.24867 Date: 2025-12-31 Authors: Yiming Liang, Yizhi Li, Yantao Du, Ge Zhang, Jiayi Zhou, Yuchen Wu, Yinzhu Piao, Denghui Cao, Tong Sun, …

Modeling Language as a Sequence of Thoughts

📝 Original Info Title: Modeling Language as a Sequence of Thoughts ArXiv ID: 2512.25026 Date: 2025-12-31 Authors: Nasim Borazjanizadeh, James McClelland 📝 Abstract Transformer language models can generate strikingly natural text by modeling language …

PrivacyBench: A Conversational Benchmark for Evaluating Privacy in Personalized AI

📝 Original Info Title: PrivacyBench: A Conversational Benchmark for Evaluating Privacy in Personalized AI ArXiv ID: 2512.24848 Date: 2025-12-31 Authors: Srija Mukhopadhyay, Sathwik Reddy, Shruthi Muthukumar, Jisun An, Ponnurangam Kumaraguru 📝 …

R-Debater: Retrieval-Augmented Debate Generation through Argumentative Memory

📝 Original Info Title: R-Debater: Retrieval-Augmented Debate Generation through Argumentative Memory ArXiv ID: 2512.24684 Date: 2025-12-31 Authors: Maoyuan Li, Zhongsheng Wang, Haoyuan Li, Jiamou Liu 📝 Abstract We present R-Debater, an agentic …

Comparing Approaches to Automatic Summarization in Less-Resourced Languages

📝 Original Info Title: Comparing Approaches to Automatic Summarization in Less-Resourced Languages ArXiv ID: 2512.24410 Date: 2025-12-30 Authors: Chester Palen-Michel, Constantine Lignos 📝 Abstract Automatic text summarization has achieved high …

Efficient Context Scaling with LongCat ZigZag Attention

📝 Original Info Title: Efficient Context Scaling with LongCat ZigZag Attention ArXiv ID: 2512.23966 Date: 2025-12-30 Authors: Chen Zhang, Yang Bai, Jiahuan Li, Anchun Gui, Keheng Wang, Feifan Liu, Guanyu Wu, Yuwei Jiang, Defei Bu, Li Wei, Haihang …

Fantastic Reasoning Behaviors and Where to Find Them: Unsupervised Discovery of the Reasoning Process

📝 Original Info Title: Fantastic Reasoning Behaviors and Where to Find Them: Unsupervised Discovery of the Reasoning Process ArXiv ID: 2512.23988 Date: 2025-12-30 Authors: Zhenyu Zhang, Shujian Zhang, John Lambert, Wenxuan Zhou, Zhangyang Wang, …

Skim-Aware Contrastive Learning for Efficient Document Representation

📝 Original Info Title: Skim-Aware Contrastive Learning for Efficient Document Representation ArXiv ID: 2512.24373 Date: 2025-12-30 Authors: Waheed Ahmed Abro, Zied Bouraoui 📝 Abstract Although transformer-based models have shown strong performance in …

NLP Computer Science Learning

Adversarial Lens: Exploiting Attention Layers to Generate Adversarial Examples for Evaluation

📝 Original Info Title: Adversarial Lens: Exploiting Attention Layers to Generate Adversarial Examples for Evaluation ArXiv ID: 2512.23837 Date: 2025-12-29 Authors: Kaustubh Dhole 📝 Abstract Recent advances in mechanistic interpretability suggest that …

December 29, 2025

Interpretable Safety Alignment via SAE-Constructed Low-Rank Subspace Adaptation

📝 Original Info Title: Interpretable Safety Alignment via SAE-Constructed Low-Rank Subspace Adaptation ArXiv ID: 2512.23260 Date: 2025-12-29 Authors: Dianyun Wang, Qingsen Ma, Yuhu Shang, Zhifeng Lu, Zhenbo Xu, Lechen Ning, Huijia Wu, Zhaofeng He 📝 …

December 29, 2025

Is Chain-of-Thought Really Not Explainability? Chain-of-Thought Can Be Faithful without Hint Verbalization

📝 Original Info Title: Is Chain-of-Thought Really Not Explainability? Chain-of-Thought Can Be Faithful without Hint Verbalization ArXiv ID: 2512.23032 Date: 2025-12-28 Authors: Kerem Zaman, Shashank Srivastava 📝 Abstract Recent work, using the …

December 28, 2025

LENS: LLM-Enabled Narrative Synthesis for Mental Health by Aligning Multimodal Sensing with Language Models

📝 Original Info Title: LENS: LLM-Enabled Narrative Synthesis for Mental Health by Aligning Multimodal Sensing with Language Models ArXiv ID: 2512.23025 Date: 2025-12-28 Authors: Wenxuan Xu, Arvind Pillai, Subigya Nepal, Amanda C Collins, Daniel M …

December 28, 2025

Break Out the Silverware -- Semantic Understanding of Stored Household Items

📝 Original Info Title: Break Out the Silverware – Semantic Understanding of Stored Household Items ArXiv ID: 2512.23739 Date: 2025-12-25 Authors: Michaela Levi-Richter, Reuth Mirsky, Oren Glickman 📝 Abstract Bring me a plate. " For domestic …

December 25, 2025

HarmTransform: Transforming Explicit Harmful Queries into Stealthy via Multi-Agent Debate

📝 Original Info Title: HarmTransform: Transforming Explicit Harmful Queries into Stealthy via Multi-Agent Debate ArXiv ID: 2512.23717 Date: 2025-12-09 Authors: Shenzhe Zhu 📝 Abstract Large language models (LLMs) are equipped with safety mechanisms to …

December 09, 2025

NLP Computer Science HCI Artificial Intelligence Machine Learning System

Survey on Evaluation Methods for Dialogue Systems

📝 Original Info Title: Survey on Evaluation Methods for Dialogue Systems ArXiv ID: 1905.04071 Date: 2020-06-29 Authors: Jan Deriu, Alvaro Rodrigo, Arantxa Otegi, Guillermo Echegoyen, Sophie Rosset, Eneko Agirre, Mark Cieliebak 📝 Abstract In this …

June 29, 2020

SirenLess: reveal the intention behind news

📝 Original Info Title: SirenLess: reveal the intention behind news ArXiv ID: 2001.02731 Date: 2020-01-10 Authors: Xumeng Chen, Leo Yu-Ho Lo, Huamin Qu 📝 Abstract News articles tend to be increasingly misleading nowadays, preventing readers from …

January 10, 2020

NLP Computer Science HCI

VOnDA: A Framework for Ontology-Based Dialogue Management

📝 Original Info Title: VOnDA: A Framework for Ontology-Based Dialogue Management ArXiv ID: 1910.00340 Date: 2019-10-02 Authors: Bernd Kiefer and Anna Welker and Christophe Biwer 📝 Abstract We present VOnDA, a framework to implement the dialogue …

October 02, 2019

NLP Framework Computer Science HCI

Contextualized Word Representations for Reading Comprehension

📝 Original Info Title: Contextualized Word Representations for Reading Comprehension ArXiv ID: 1712.03609 Date: 2018-09-05 Authors: Shimi Salant, Jonathan Berant 📝 Abstract Reading a document and extracting an answer to a question about its content …

September 05, 2018

A Co-Matching Model for Multi-choice Reading Comprehension

📝 Original Info Title: A Co-Matching Model for Multi-choice Reading Comprehension ArXiv ID: 1806.04068 Date: 2018-06-12 Authors: Shuohang Wang, Mo Yu, Shiyu Chang, Jing Jiang 📝 Abstract Multi-choice reading comprehension is a challenging task, which …

June 12, 2018

NLP Data Computer Science System

No Image

Selecting Machine-Translated Data for Quick Bootstrapping of a Natural Language Understanding System

📝 Original Info Title: Selecting Machine-Translated Data for Quick Bootstrapping of a Natural Language Understanding System ArXiv ID: 1805.09119 Date: 2018-05-24 Authors: Judith Gaspers and Penny Karanasou and Rajen Chatterjee 📝 Abstract This paper …

May 24, 2018

Multi-Passage Machine Reading Comprehension with Cross-Passage Answer Verification

📝 Original Info Title: Multi-Passage Machine Reading Comprehension with Cross-Passage Answer Verification ArXiv ID: 1805.02220 Date: 2018-05-11 Authors: Yizhong Wang, Kai Liu, Jing Liu, Wei He, Yajuan Lyu, Hua Wu, Sujian Li and Haifeng Wang 📝 …

May 11, 2018