📄 Paper Explainer

Recent Papers from arXiv

• arXiv:2607.09623
  Task-Specific Multimodal Question Answering Agents via Confidence Calibration and Incremental Reasoning for QANTA 2026
  Nirjhar Das, Md. Al-Mamun Provath
  Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
• arXiv:2607.09611
  Toward Real-Time Sentence-Level Sign Language Translation
  Thanh-Hoang Nguyen Doan (The University of Danang - University of Science and Technology)
  Computation and Language (cs.CL)
• arXiv:2607.09598
  Tokenizer Transplantation: Mitigating Autoregressive Collapse in Edge-Efficient Bengali ASR
  Sanjid Hasan, Md. Abdur Rahman
  Computation and Language (cs.CL)
• arXiv:2607.09576
  Conceptual Networks for Cross-Linguistic Idiomatic Expressions:A Feature-Based Graph Approach
  Kiran Pala, Punam Silu, Lixun Yu
  Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Emerging Technologies (cs.ET)
• arXiv:2607.09530
  FreyaTTS Technical Report
  Ahmet Erdem Pamuk, Ömer Yentür, Ahmet Tunga Bayrak, et al.
  Computation and Language (cs.CL)
• arXiv:2607.09501
  Normalisation-Based Likelihood Ratio Estimation for Forensic Authorship Verification
  Sadie Barlow, Andrea Nini, Edoardo Manino
  Computation and Language (cs.CL); Applications (stat.AP)
• arXiv:2607.09438
  Test-Time Scaling for Small VLMs on Multilingual Visual MCQ
  Spiros Baxevanakis, Peng-Jian Yang
  Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
• arXiv:2607.09424
  A Sovereign, Open-Source Foundation Model for German and English
  The Soofi-Team: Benedikt Droste, David Fitzek, Ruben Härle, et al.
  Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
• arXiv:2607.09415
  Self-Guided Test-Time Training for Long-Context LLMs
  Xinyu Zhu, Zhe Xu, Xiaohan Wei, et al.
  Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
• arXiv:2607.09349
  Deceptive Grounding: Entity Attribution Failure in Clinical Retrieval-Augmented Generation
  Cedric Caruzzo, Donggeun Yoo, Tae Soo Kim
  Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
• arXiv:2607.09348
  DKCD: Domain Knowledge-Enhanced Causal Discovery from Unstructured Data
  Xin Li, Jin Li, Shoujin Wang, et al.
  Computation and Language (cs.CL)
• arXiv:2607.09338
  Towards Detecting Inconsistencies in End-to-end Generated TODs
  Tiziano Labruna, Giovanni Bonetta, Bernardo Magnini
  Computation and Language (cs.CL); Symbolic Computation (cs.SC)
• arXiv:2607.09328
  WILDTRACE: Benchmarking Natural Evidence Trails in Long-Context Reasoning
  Zixin Chen, Peng Liu, Haobo Li, et al.
  Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
• arXiv:2607.09324
  Letting the Data Speak: Extracting Keywords from Crowdsourced Collections with AI
  Miguel Arana-Catania, Catherine Conisbee, Matthew Kidd
  Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Digital Libraries (cs.DL); Information Retrieval (cs.IR); Machine Learning (cs.LG)
• arXiv:2607.09316
  Automatic Thematic Indexing of Large Literary Corpora: A Machine Learning Approach to Voltaire's Complete Works
  Miguel Arana-Catania, Gillian Pink, Glenn Roe
  Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Digital Libraries (cs.DL); Information Retrieval (cs.IR); Machine Learning (cs.LG)
• arXiv:2607.09306
  Creativity, honesty and designed forgetting emerge in small hyperbolic language models
  Kwan Soo Shin, In Seok Kang, Yunkyung Min
  Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC); Machine Learning (cs.LG)
• arXiv:2607.09291
  Letter Lemmatization: One-to-one and Banded RNNs for Reversing Character-Set Simplification and Abbreviation in Medieval Text
  Anguelos Nicolaou, Maria Pia Tiseo, Tamas Kovacs, et al.
  Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV)
• arXiv:2607.09204
  Complexity-Guided Component-wise Initialization for Language Model Pretraining
  Konstantin Garbers, Nicholas Oh
  Computation and Language (cs.CL); Machine Learning (cs.LG)
• arXiv:2607.09121
  Augmenting Fundamental Analysis with Large Language Models: A RAG-Based System for Generating Investor Briefs
  Bartosz Ziółko, Kacper Dobrzeniewski
  Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Portfolio Management (q-fin.PM); Trading and Market Microstructure (q-fin.TR)
• arXiv:2607.09094
  PRecG: Legal Precedent Retrieval with Graph Neural Networks and Rhetorical Role Segmentation
  Devanshu Verma, Vasudha Bhatnagar, Vikas Kumar, et al.
  Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
• arXiv:2607.09092
  AgentKGV: Agentic LLM-RAG Framework with Two-Stage Training for the Fact Verification of Knowledge Graphs
  Yumin Heo, Hyeon-gu Lee, Sumin Seo, et al.
  Computation and Language (cs.CL)
• arXiv:2607.09053
  An Emergent Mirage: Is Emergent Misalignment and Realignment Indeed a Robust Phenomenon?
  Abhinav Rao, Liancheng Gong, Bin Hu, et al.
  Computation and Language (cs.CL)
• arXiv:2607.08775
  HALO: Hybrid Adaptive Latent Reasoning for Language Models
  Micah Zhang
  Computation and Language (cs.CL); Machine Learning (cs.LG)
• arXiv:2607.09600
  Agora: Enhancing LLM Agent Reasoning Via Auction-Based Task Allocation
  Kaiji Zhou, Ales Leonardis, Yue Feng
  Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
• arXiv:2607.09487
  Neural Collapse Is Forbidden: Information Floors in Language Models
  Bruno Abrahao
  Machine Learning (cs.LG); Computation and Language (cs.CL); Machine Learning (stat.ML)