📄 Paper Explainer

Recent Papers from arXiv

• arXiv:2606.03982
  Language Models Compare Quantities Using Number-specific and Unit-specific Heuristics
  Mutsumi Sasaki, Go kamoda, Ryosuke Takahashi, et al.
  Computation and Language (cs.CL)
• arXiv:2606.03969
  Quantifying Faithful Confidence Expression in Large Reasoning Models
  Areeb Gani, Asal Meskin, Gabrielle Kaili-May Liu, et al.
  Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
• arXiv:2606.03968
  QUBRIC: Co-Designing Queries and Rubrics for RL Beyond Verifiable Rewards
  Rongzhi Zhang, Rui Feng, Zhihan Zhang, et al.
  Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
• arXiv:2606.03967
  AlignAtt4LLM: Fast AlignAtt for Decoder-Only LLMs at IWSLT 2026 Simultaneous Speech Translation Task
  Quentin Fuxa, Dominik Macháček
  Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
• arXiv:2606.03965
  Agentic Chain-of-Thought Steering for Efficient and Controllable LLM Reasoning
  Yu Xia, Zhouhang Xie, Xin Xu, et al.
  Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
• arXiv:2606.03957
  Efficient ASR Training with Conversations that Never Happened
  Máté Gedeon, Péter Mihajlik
  Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Sound (cs.SD); Audio and Speech Processing (eess.AS)
• arXiv:2606.03948
  A Pocket Offline Model for Simultaneous Speech Translation as CUNI Submission to IWSLT 2026
  Aziz Sharipov Ortega, Dominik Macháček
  Computation and Language (cs.CL)
• arXiv:2606.03924
  Knowledge Editing in Masked Diffusion Language Models
  Haewon Park, Yohan Jo
  Computation and Language (cs.CL)
• arXiv:2606.03892
  Synthesize and Reward -- Reinforcement Learning for Multi-Step Tool Use in Live Environments
  Ibrahim Abdelaziz, Asim Munawar, Kinjal Basu, et al.
  Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
• arXiv:2606.03889
  RealClawBench: Live OpenClaw Benchmarks from Real Developer-Agent Sessions
  Zongwei Lv, Zhewen Tan, Yaoming Li, et al.
  Computation and Language (cs.CL)
• arXiv:2606.03867
  A Training-Free Mixture-of-Agents Framework for Multi-Document Summarization using LLMs and Knowledge Graphs
  Cuong Vuong Tuan, Trang Mai Xuan, Tien-Cuong Nguyen, et al.
  Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
• arXiv:2606.03846
  Clustered Self-Assessment: A Simple yet Effective Method for Uncertainty Quantification in Large Language Models
  Qi Cao, Takeshi Kojima, Andrew Gambardella, et al.
  Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
• arXiv:2606.03817
  Rethinking the Idiomaticity Decomposability Hypothesis: Evidence from Distributional Learning
  Maggie Mi, Golzar Atefi, Atsuki Yamaguchi, et al.
  Computation and Language (cs.CL)
• arXiv:2606.03810
  Consistency Training Can Entrench Misalignment
  David Demitri Africa, Arathi Mani
  Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
• arXiv:2606.03793
  Exploring Adversarial Robustness and Safety Alignment in Multilingual Multi-Modal Large Language Models
  Hashmat Shadab Malik, Muzammal Naseer, Salman Khan
  Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV)
• arXiv:2606.03785
  Backdoor Unlearning Generalization: A Path Toward the Removal of Unknown Triggers in LLMs
  Lisa Bouger, Théo Lasnier, Philippe Looubet Moundi, et al.
  Computation and Language (cs.CL)
• arXiv:2606.03782
  Reasoning over Grammar: Can Synthetic Linguistic Reasoning Traces Enhance Low-Resource Machine Translation?
  Renhao Pei, Yihong Liu, Sampo Pyysalo, et al.
  Computation and Language (cs.CL)
• arXiv:2606.03780
  Expert-Aware Causal Tracing of Factual Recall in Sparse MoE Language Models
  Yuetian Lu, Ali Modarressi, Yihong Liu, et al.
  Computation and Language (cs.CL); Machine Learning (cs.LG)
• arXiv:2606.03773
  KletterMix: Climbing Toward High-Quality German Pretraining Data
  Maurice Kraus, Ruben Härle, Sebastian Sztwiertnia, et al.
  Computation and Language (cs.CL)
• arXiv:2606.03768
  HybridThinker: Efficient Chain-of-Thought Reasoning via Compressed Memory and Transient Thought Steps
  Xin Liu, Runsong Zhao, Xinyu Liu, et al.
  Computation and Language (cs.CL)
• arXiv:2606.03761
  Framing Migration News with LLMs: Structured CoT as a Support for Human Interpretation
  David Alonso del Barrio, Jing Wen, Daniel Gatica-Perez
  Computation and Language (cs.CL)
• arXiv:2606.03739
  Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines
  Justice Owusu Agyemang, Jerry John Kponyo, Kwame Opuni-Boachie Obour Agyekum, et al.
  Computation and Language (cs.CL); Information Theory (cs.IT)
• arXiv:2606.03728
  Re-Ranking Through an Attribution Lens for Citation Quality in Legal QA
  Mohamed Hesham Elganayni, Selim Saleh
  Computation and Language (cs.CL); Information Retrieval (cs.IR)
• arXiv:2606.03695
  Don't Forget Your Embeddings: Robust Knowledge Erasure via Precise Editing of Embeddings
  Clara Haya Suslik, Or Shafran, Mor Geva
  Computation and Language (cs.CL)
• arXiv:2606.03693
  Does Language Shift Break Medical Vision-Language Models? Indonesian Radiology Visual Question Answering Case Study
  Pieter Christy Yan Yudhistira, Dzaki Rafif Malik, Novanto Yudistira
  Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV)