arXiv cs.CL Computation and Language
@cscl-bot.bsky.social
Unofficial bot by @vele.bsky.social w/ http://github.com/so-okada/bXiv https://arxiv.org/list/cs.CL/new
List https://bsky.app/profile/vele.bsky.social/lists/3lim7ccweqo2j
ModList https://bsky.app/profile/vele.bsky.social/lists/3lim3qnexsw2g
List https://bsky.app/profile/vele.bsky.social/lists/3lim7ccweqo2j
ModList https://bsky.app/profile/vele.bsky.social/lists/3lim3qnexsw2g
Reposted by arXiv cs.CL Computation and Language
Suhyung Jang, Ghang Lee, Jaekun Lee, Hyunjun Lee: Enhancing Building Semantics Preservation in AI Model Training with Large Language Model Encodings https://arxiv.org/abs/2602.15791 https://arxiv.org/pdf/2602.15791 https://arxiv.org/html/2602.15791
February 18, 2026 at 6:29 AM
Suhyung Jang, Ghang Lee, Jaekun Lee, Hyunjun Lee: Enhancing Building Semantics Preservation in AI Model Training with Large Language Model Encodings https://arxiv.org/abs/2602.15791 https://arxiv.org/pdf/2602.15791 https://arxiv.org/html/2602.15791
Reposted by arXiv cs.CL Computation and Language
5 Team, et al.: GLM-5: from Vibe Coding to Agentic Engineering https://arxiv.org/abs/2602.15763 https://arxiv.org/pdf/2602.15763 https://arxiv.org/html/2602.15763
February 18, 2026 at 6:33 AM
5 Team, et al.: GLM-5: from Vibe Coding to Agentic Engineering https://arxiv.org/abs/2602.15763 https://arxiv.org/pdf/2602.15763 https://arxiv.org/html/2602.15763
Reposted by arXiv cs.CL Computation and Language
Sarim Chaudhry: Recursive Concept Evolution for Compositional Reasoning in Large Language Models https://arxiv.org/abs/2602.15725 https://arxiv.org/pdf/2602.15725 https://arxiv.org/html/2602.15725
February 18, 2026 at 6:29 AM
Sarim Chaudhry: Recursive Concept Evolution for Compositional Reasoning in Large Language Models https://arxiv.org/abs/2602.15725 https://arxiv.org/pdf/2602.15725 https://arxiv.org/html/2602.15725
Reposted by arXiv cs.CL Computation and Language
Rehana Mahfuz, Yinyi Guo, Erik Visser, Phanidhar Chinchili: Proactive Conversational Assistant for a Procedural Manual Task based on Audio and IMU https://arxiv.org/abs/2602.15707 https://arxiv.org/pdf/2602.15707 https://arxiv.org/html/2602.15707
February 18, 2026 at 6:33 AM
Rehana Mahfuz, Yinyi Guo, Erik Visser, Phanidhar Chinchili: Proactive Conversational Assistant for a Procedural Manual Task based on Audio and IMU https://arxiv.org/abs/2602.15707 https://arxiv.org/pdf/2602.15707 https://arxiv.org/html/2602.15707
Reposted by arXiv cs.CL Computation and Language
Conte, Mattiace, Carmosino, Aghilar, Servedio, Musicco, Anelli, Di Noia, Donini: RUVA: Personalized Transparent On-Device Graph Reasoning https://arxiv.org/abs/2602.15553 https://arxiv.org/pdf/2602.15553 https://arxiv.org/html/2602.15553
February 18, 2026 at 6:29 AM
Conte, Mattiace, Carmosino, Aghilar, Servedio, Musicco, Anelli, Di Noia, Donini: RUVA: Personalized Transparent On-Device Graph Reasoning https://arxiv.org/abs/2602.15553 https://arxiv.org/pdf/2602.15553 https://arxiv.org/html/2602.15553
Reposted by arXiv cs.CL Computation and Language
Zhouzhou Shen, Xueyu Hu, Xiyun Li, Tianqing Fang, Juncheng Li, Shengyu Zhang: World-Model-Augmented Web Agents with Action Correction https://arxiv.org/abs/2602.15384 https://arxiv.org/pdf/2602.15384 https://arxiv.org/html/2602.15384
February 18, 2026 at 6:29 AM
Zhouzhou Shen, Xueyu Hu, Xiyun Li, Tianqing Fang, Juncheng Li, Shengyu Zhang: World-Model-Augmented Web Agents with Action Correction https://arxiv.org/abs/2602.15384 https://arxiv.org/pdf/2602.15384 https://arxiv.org/html/2602.15384
Reposted by arXiv cs.CL Computation and Language
Edward Chen, Sanmi Koyejo, Carlos Guestrin: Discovering Implicit Large Language Model Alignment Objectives https://arxiv.org/abs/2602.15338 https://arxiv.org/pdf/2602.15338 https://arxiv.org/html/2602.15338
February 18, 2026 at 6:33 AM
Edward Chen, Sanmi Koyejo, Carlos Guestrin: Discovering Implicit Large Language Model Alignment Objectives https://arxiv.org/abs/2602.15338 https://arxiv.org/pdf/2602.15338 https://arxiv.org/html/2602.15338
Reposted by arXiv cs.CL Computation and Language
Hanlin Zhang, Jikai Jin, Vasilis Syrgkanis, Sham Kakade: Prescriptive Scaling Reveals the Evolution of Language Model Capabilities https://arxiv.org/abs/2602.15327 https://arxiv.org/pdf/2602.15327 https://arxiv.org/html/2602.15327
February 18, 2026 at 6:33 AM
Hanlin Zhang, Jikai Jin, Vasilis Syrgkanis, Sham Kakade: Prescriptive Scaling Reveals the Evolution of Language Model Capabilities https://arxiv.org/abs/2602.15327 https://arxiv.org/pdf/2602.15327 https://arxiv.org/html/2602.15327
Reposted by arXiv cs.CL Computation and Language
Kiho Park, Todd Nief, Yo Joong Choe, Victor Veitch: The Information Geometry of Softmax: Probing and Steering https://arxiv.org/abs/2602.15293 https://arxiv.org/pdf/2602.15293 https://arxiv.org/html/2602.15293
February 18, 2026 at 6:32 AM
Kiho Park, Todd Nief, Yo Joong Choe, Victor Veitch: The Information Geometry of Softmax: Probing and Steering https://arxiv.org/abs/2602.15293 https://arxiv.org/pdf/2602.15293 https://arxiv.org/html/2602.15293
Reposted by arXiv cs.CL Computation and Language
Victor De Lima, Jiqun Liu, Grace Hui Yang: FrameRef: A Framing Dataset and Simulation Testbed for Modeling Bounded Rational Information Health https://arxiv.org/abs/2602.15273 https://arxiv.org/pdf/2602.15273 https://arxiv.org/html/2602.15273
February 18, 2026 at 6:30 AM
Victor De Lima, Jiqun Liu, Grace Hui Yang: FrameRef: A Framing Dataset and Simulation Testbed for Modeling Bounded Rational Information Health https://arxiv.org/abs/2602.15273 https://arxiv.org/pdf/2602.15273 https://arxiv.org/html/2602.15273
Reposted by arXiv cs.CL Computation and Language
Austin Veselka: How to Train Your Long-Context Visual Document Model https://arxiv.org/abs/2602.15257 https://arxiv.org/pdf/2602.15257 https://arxiv.org/html/2602.15257
February 18, 2026 at 6:30 AM
Austin Veselka: How to Train Your Long-Context Visual Document Model https://arxiv.org/abs/2602.15257 https://arxiv.org/pdf/2602.15257 https://arxiv.org/html/2602.15257
Reposted by arXiv cs.CL Computation and Language
Nakamura, Kumar, Das, Abdelnabi, Mahmud, Fioretto, Zilberstein, Bagdasarian: Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems https://arxiv.org/abs/2602.15198 https://arxiv.org/pdf/2602.15198 https://arxiv.org/html/2602.15198
February 18, 2026 at 6:32 AM
Nakamura, Kumar, Das, Abdelnabi, Mahmud, Fioretto, Zilberstein, Bagdasarian: Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems https://arxiv.org/abs/2602.15198 https://arxiv.org/pdf/2602.15198 https://arxiv.org/html/2602.15198
Reposted by arXiv cs.CL Computation and Language
David Puertolas Merenciano, Ekaterina Vasyagina, Raghav Dixit, Kevin Zhu, Ruizhe Li, Javier Ferrando, Maheep Chaudhary: Weight space Detection of Backdoors in LoRA Adapters https://arxiv.org/abs/2602.15195 https://arxiv.org/pdf/2602.15195 https://arxiv.org/html/2602.15195
February 18, 2026 at 6:30 AM
David Puertolas Merenciano, Ekaterina Vasyagina, Raghav Dixit, Kevin Zhu, Ruizhe Li, Javier Ferrando, Maheep Chaudhary: Weight space Detection of Backdoors in LoRA Adapters https://arxiv.org/abs/2602.15195 https://arxiv.org/pdf/2602.15195 https://arxiv.org/html/2602.15195
Reposted by arXiv cs.CL Computation and Language
William Brach, Francesco Zuppichini, Marco Vinciguerra, Lorenzo Padoan: ScrapeGraphAI-100k: A Large-Scale Dataset for LLM-Based Web Information Extraction https://arxiv.org/abs/2602.15189 https://arxiv.org/pdf/2602.15189 https://arxiv.org/html/2602.15189
February 18, 2026 at 6:32 AM
William Brach, Francesco Zuppichini, Marco Vinciguerra, Lorenzo Padoan: ScrapeGraphAI-100k: A Large-Scale Dataset for LLM-Based Web Information Extraction https://arxiv.org/abs/2602.15189 https://arxiv.org/pdf/2602.15189 https://arxiv.org/html/2602.15189
Reposted by arXiv cs.CL Computation and Language
Nicolas Buzeta, Felipe del Rio, Cristian Hinostroza, Denis Parra, Hans Lobel, Rodrigo Toro Icarte: Seeing to Generalize: How Visual Data Corrects Binding Shortcuts https://arxiv.org/abs/2602.15183 https://arxiv.org/pdf/2602.15183 https://arxiv.org/html/2602.15183
February 18, 2026 at 6:32 AM
Nicolas Buzeta, Felipe del Rio, Cristian Hinostroza, Denis Parra, Hans Lobel, Rodrigo Toro Icarte: Seeing to Generalize: How Visual Data Corrects Binding Shortcuts https://arxiv.org/abs/2602.15183 https://arxiv.org/pdf/2602.15183 https://arxiv.org/html/2602.15183
Reposted by arXiv cs.CL Computation and Language
Xinhang Ma, William Yeoh, Ning Zhang, Yevgeniy Vorobeychik: Protecting Language Models Against Unauthorized Distillation through Trace Rewriting https://arxiv.org/abs/2602.15143 https://arxiv.org/pdf/2602.15143 https://arxiv.org/html/2602.15143
February 18, 2026 at 6:29 AM
Xinhang Ma, William Yeoh, Ning Zhang, Yevgeniy Vorobeychik: Protecting Language Models Against Unauthorized Distillation through Trace Rewriting https://arxiv.org/abs/2602.15143 https://arxiv.org/pdf/2602.15143 https://arxiv.org/html/2602.15143
Devang Acharya, Mohammad Hammoud: Avey-B https://arxiv.org/abs/2602.15814 https://arxiv.org/pdf/2602.15814 https://arxiv.org/html/2602.15814
February 18, 2026 at 6:30 AM
Devang Acharya, Mohammad Hammoud: Avey-B https://arxiv.org/abs/2602.15814 https://arxiv.org/pdf/2602.15814 https://arxiv.org/html/2602.15814
Quentin Lemesle, L\'eane Jourdan, Daisy Munson, Pierre Alain, Jonathan Chevelu, Arnaud Delhay, Damien Lolive: *-PLUIE: Personalisable metric with Llm Used for Improved Evaluation https://arxiv.org/abs/2602.15778 https://arxiv.org/pdf/2602.15778 https://arxiv.org/html/2602.15778
February 18, 2026 at 6:30 AM
Quentin Lemesle, L\'eane Jourdan, Daisy Munson, Pierre Alain, Jonathan Chevelu, Arnaud Delhay, Damien Lolive: *-PLUIE: Personalisable metric with Llm Used for Improved Evaluation https://arxiv.org/abs/2602.15778 https://arxiv.org/pdf/2602.15778 https://arxiv.org/html/2602.15778
Yahia Alqurnawi, Preetom Biswas, Anmol Rao, Tejas Anvekar, Chitta Baral, Vivek Gupta: ViTaB-A: Evaluating Multimodal Large Language Models on Visual Table Attribution https://arxiv.org/abs/2602.15769 https://arxiv.org/pdf/2602.15769 https://arxiv.org/html/2602.15769
February 18, 2026 at 6:30 AM
Yahia Alqurnawi, Preetom Biswas, Anmol Rao, Tejas Anvekar, Chitta Baral, Vivek Gupta: ViTaB-A: Evaluating Multimodal Large Language Models on Visual Table Attribution https://arxiv.org/abs/2602.15769 https://arxiv.org/pdf/2602.15769 https://arxiv.org/html/2602.15769
Manav Nitin Kapadnis, Lawanya Baghel, Atharva Naik, Carolyn Ros\'e: ChartEditBench: Evaluating Grounded Multi-Turn Chart Editing in Multimodal Language Models https://arxiv.org/abs/2602.15758 https://arxiv.org/pdf/2602.15758 https://arxiv.org/html/2602.15758
February 18, 2026 at 6:30 AM
Manav Nitin Kapadnis, Lawanya Baghel, Atharva Naik, Carolyn Ros\'e: ChartEditBench: Evaluating Grounded Multi-Turn Chart Editing in Multimodal Language Models https://arxiv.org/abs/2602.15758 https://arxiv.org/pdf/2602.15758 https://arxiv.org/html/2602.15758
Laura De Grazia, Danae S\'anchez Villegas, Desmond Elliott, Mireia Farr\'us, Mariona Taul\'e: Beyond Binary Classification: Detecting Fine-Grained Sexism in Social Media Videos https://arxiv.org/abs/2602.15757 https://arxiv.org/pdf/2602.15757 https://arxiv.org/html/2602.15757
February 18, 2026 at 6:30 AM
Laura De Grazia, Danae S\'anchez Villegas, Desmond Elliott, Mireia Farr\'us, Mariona Taul\'e: Beyond Binary Classification: Detecting Fine-Grained Sexism in Social Media Videos https://arxiv.org/abs/2602.15757 https://arxiv.org/pdf/2602.15757 https://arxiv.org/html/2602.15757
Chahan Vidal-Gor\`ene, Bastien Kindt, Florian Cafiero: Under-resourced studies of under-resourced languages: lemmatization and POS-tagging with LLM annotators for historical Armenian, Georgia... https://arxiv.org/abs/2602.15753 https://arxiv.org/pdf/2602.15753 https://arxiv.org/html/2602.15753
February 18, 2026 at 6:30 AM
Chahan Vidal-Gor\`ene, Bastien Kindt, Florian Cafiero: Under-resourced studies of under-resourced languages: lemmatization and POS-tagging with LLM annotators for historical Armenian, Georgia... https://arxiv.org/abs/2602.15753 https://arxiv.org/pdf/2602.15753 https://arxiv.org/html/2602.15753
Omri Feldman, Amar Venugopal, Jann Spiess, Amir Feder: Causal Effect Estimation with Latent Textual Treatments https://arxiv.org/abs/2602.15730 https://arxiv.org/pdf/2602.15730 https://arxiv.org/html/2602.15730
February 18, 2026 at 6:30 AM
Omri Feldman, Amar Venugopal, Jann Spiess, Amir Feder: Causal Effect Estimation with Latent Textual Treatments https://arxiv.org/abs/2602.15730 https://arxiv.org/pdf/2602.15730 https://arxiv.org/html/2602.15730
Roksana Goworek, Haim Dubossarsky: Rethinking Metrics for Lexical Semantic Change Detection https://arxiv.org/abs/2602.15716 https://arxiv.org/pdf/2602.15716 https://arxiv.org/html/2602.15716
February 18, 2026 at 6:30 AM
Roksana Goworek, Haim Dubossarsky: Rethinking Metrics for Lexical Semantic Change Detection https://arxiv.org/abs/2602.15716 https://arxiv.org/pdf/2602.15716 https://arxiv.org/html/2602.15716
Meirav Segal, Noa Linder, Omer Antverg, Gil Gekker, Tomer Fichman, Omri Bodenheimer, Edan Maor, Omer Nevo: A Content-Based Framework for Cybersecurity Refusal Decisions in Large Language Models https://arxiv.org/abs/2602.15689 https://arxiv.org/pdf/2602.15689 https://arxiv.org/html/2602.15689
February 18, 2026 at 6:30 AM
Meirav Segal, Noa Linder, Omer Antverg, Gil Gekker, Tomer Fichman, Omri Bodenheimer, Edan Maor, Omer Nevo: A Content-Based Framework for Cybersecurity Refusal Decisions in Large Language Models https://arxiv.org/abs/2602.15689 https://arxiv.org/pdf/2602.15689 https://arxiv.org/html/2602.15689