Natural language processing

Classical and neural NLP: translation, question answering, tokenization and the evaluation of language understanding.

2,700 stories · RSS feed

arXiv Machine Learning

Jul 2

GryphOne: Symbol-Aware Masked Diffusion for Structural Refinement in Offline Handwritten Mathematical Expression Recognition

arXiv:2602. 03370v2 Announce Type: replace-cross Abstract: Handwritten mathematical expression recognition (HMER) requires reasoning over diverse symbols and structures, yet autoregressive models struggle with exposure bias and syntax inconsistency.

By Takaya Kawakatsu, Ryo Ishiyama

diffusion nlp benchmarks safety

arXiv Machine Learning

Jul 2

Message Passing Enables Efficient Reasoning

arXiv:2607. 01077v1 Announce Type: cross Abstract: While inference-time scaling has improved the reasoning abilities of large language models (LLMs), the need to generate long chains-of-thought (CoTs) is a computational bottleneck.

By Xuecheng Liu, Daman Arora, Gokul Swamy, Andrea Zanette

llms nlp fine-tuning

arXiv AI

Jul 2

Knowdit: Agentic Smart Contract Vulnerability Detection with Auditing Knowledge Summarization

arXiv:2603. 26270v2 Announce Type: replace-cross Abstract: Smart contracts govern billions of dollars in decentralized finance (DeFi), yet automated vulnerability detection remains challenging because many vulnerabilities are tightly coupled with project-specific business logic.

By Ziqiao Kong, Wanxu Xia, Chong Wang, Yue Xue, Yi Lu, Pan Li, Shaohua Li, Zong Cao, Yang Liu

agents nlp

arXiv AI

Jul 2

The Illusion of High Utility in Safety Alignment of Text-to-Image Diffusion Models

arXiv:2607. 00402v1 Announce Type: cross Abstract: Safety alignment of text-to-image (T2I) diffusion models aims to suppress harmful generations while preserving utility on benign prompts.

By Adeel Yousaf, Soumik Ghosh, James Beetham, Amrit Singh Bedi, Mubarak Shah

rag diffusion nlp benchmarks safety

arXiv AI

Jul 2

Comparing Large Language Models on Scrum Certification-Style Questions: Accuracy, Stability, and Error Patterns

arXiv:2607. 00048v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used in exam- and certification-style question answering tasks, where their ability to retrieve, interpret, and apply domain-specific knowledge can be systematically assessed.

By Robson Alves Vilar, Emanuel Dantas Filho, Ademar Fran\c{c}a de Sousa Neto, Mirko Perkusich, Danyllo Wagner Albuquerque, Jo\~ao Paiva, Kyller Gorg\^onio, Angelo Perkusich

llms nlp

arXiv AI

Jul 2

Bayesian Uncertainty Propagation for Agentic RAG Pipelines: A Proof-of-Concept Study on Multi-Hop Question Answering

arXiv:2607. 00972v1 Announce Type: new Abstract: Trustworthy deployment of Agentic Retrieval-Augmented Generation (RAG) systems requires mechanisms for estimating when multi-stage reasoning pipelines may fail.

By Louis Donaldson, Connor Walker, Koorosh Aslansefat, Yiannis Papadopoulos

llms rag agents nlp

arXiv AI

Jul 2

Memory-Native Non-Terrestrial Networks for Embodied Intelligence

arXiv:2607. 00029v1 Announce Type: cross Abstract: Non-terrestrial networks (NTN) provide ubiquitous connectivity for embodied intelligence (EI), enabling robots in wilderness to leverage cloud resources or report critical information to remote centers.

By Chengyang Li, Yikun Wang, Jiahui He, Yujie Wan, Shuai Wang, Yuan Wu, Yik-Chung Wu, Chengzhong Xu, Huseyin Arslan

nlp robotics

arXiv AI

Jul 2

XSkill: Continual Learning from Experience and Skills in Multimodal Agents

arXiv:2603. 12056v3 Announce Type: replace Abstract: Multimodal agents can now tackle complex reasoning tasks with diverse tools, yet they still suffer from inefficient tool use and inflexible orchestration in open-ended settings.

By Guanyu Jiang, Zhaochen Su, Xiaoye Qu, Yi R. Fung

agents nlp multimodal benchmarks

arXiv AI

Jul 2

Crystalite: A Lightweight Transformer for Efficient Crystal Modeling

arXiv:2604. 02270v2 Announce Type: replace-cross Abstract: Generative models for crystalline materials often rely on equivariant graph neural networks, which capture geometric structure well but are costly to train and slow to sample.

By Tin Had\v{z}i Veljkovi\'c, Joshua Rosenthal, Ivor Lon\v{c}ari\'c, Jan-Willem van de Meent

llms diffusion nlp benchmarks

arXiv Machine Learning

Jul 2

REALM: Reliable Expertise-Aware Language Model Fine-Tuning from Noisy Annotations

arXiv:2604. 17289v2 Announce Type: replace Abstract: Supervised fine-tuning of large language models relies on human-annotated data, yet annotation pipelines routinely involve multiple crowdworkers of heterogeneous expertise.

By Sajjad Ghiasvand, Mark Beliaev, Mahnoosh Alizadeh, Ramtin Pedarsani

llms nlp fine-tuning benchmarks safety

Towards Data Science

Jul 1

Persistent Latent Memory for Multi-Hop LLM Agents: How a 6G Handover Paper Closes the Agent Cold-Start

Every hand-off in your multi-agent pipeline is an expensive tokenization round-trip. Discover how Inductive Latent Context Persistence (ILCP) transfers a compressed hidden state so downstream agents never have to re-create the same context.

By Anubhab Banerjee

llms agents nlp

Berkeley AI Research

Jul 1

2026 BAIR Graduate Showcase

Congratulations to the Berkeley Artificial Intelligence Research (BAIR) Lab class of 2026! This year, BAIR celebrates another remarkable group of Ph.

llms rag agents diffusion computer-vision nlp reinforcement-learning robotics multimodal benchmarks safety

arXiv AI

Jul 1

ALM2Vec: Learning Audio Embeddings for Universal Audio Retrieval with Large Audio-Language Models

arXiv:2606. 30682v1 Announce Type: cross Abstract: Recent advances in language--audio retrieval have been largely driven by contrastive dual-encoder architectures that align audio and text in a shared embedding space.

By Fengjie Lu, Chenang Jiang, Jiarui Hai, Helin Wang, Aaron Yee

llms rag nlp multimodal benchmarks

arXiv Machine Learning

Jul 1

InfoFlow KV: Information-Flow-Aware KV Recomputation for Long Context

arXiv:2603. 05353v2 Announce Type: replace Abstract: Retrieval-augmented generation (RAG) for long-context question answering is bottlenecked by inference-time prefilling over large retrieved contexts.

By Xin Teng, Canyu Zhang, Shaoyi Zheng, Danyang Zhuo, Tianyi Zhou, Shenji Wan

llms rag nlp multimodal benchmarks

arXiv AI

Jul 1

Measuring & Mitigating Over-Alignment for LLMs in Multilingual Criminal Law Courts

arXiv:2606. 23375v2 Announce Type: replace-cross Abstract: While the wider applicability of LLMs in the legal field is currently debated due to their reliability and the gravity of any errors, narrow uses with well-understood and mitigated risks have emerged.

By Arthur Wuhrmann, Gaetan Stein, Daniel Brunner, Andrei Kucharavy

llms nlp benchmarks safety

arXiv AI

Jul 1

Mantis: Lightweight Foundation Model for Time Series Classification

arXiv:2502. 15637v2 Announce Type: replace-cross Abstract: While foundation models have revolutionized various domains, their application to time series classification remains rather under-explored, with existing literature predominantly focused on forecasting.

By Vasilii Feofanov, Songkang Wen, Shifeng Xie, Simon Roschmann, Marius Alonso, Hongbo Guo, Romain Ilbert, Malik Tiomoko, Quentin Bouniot, Zeynep Akata, Lujia Pan, Jianfeng Zhang, Ievgen Redko

llms rag nlp benchmarks

arXiv AI

Jul 1

Cross-Domain Feature Expansion for Tabular Medical Data via Knowledge Graphs Injection

arXiv:2606. 31171v1 Announce Type: new Abstract: Acquiring comprehensive cross-domain biomedical profiles is often costly and time-consuming, resulting in severe data scarcity in medical research.

By Mengying Zhou, Yongjie Yin, Haoyan Xin, Guoping Liu, Yang Chen

nlp benchmarks

arXiv AI

Jul 1

HistoriQA-ThirdRepublic: Multi-Hop Question Answering Corpus for Historical Research, Parliamentary Debates from the French Third Republic (1870-1940)

arXiv:2606. 31325v1 Announce Type: new Abstract: We present HistoriQA-ThirdRepublic: a French-language dataset of multi-hop historical questions derived from parliamentary debates and newspapers of the French Third Republic.

By Aur\'elien Pellet (LRE), Julien Perez (EPITA, LRE), Marie Puren (LRE, CJM)

llms rag nlp benchmarks safety

arXiv Machine Learning

Jul 1

Symmetry in language statistics shapes the geometry of model representations

arXiv:2602. 15029v3 Announce Type: replace Abstract: The internal representations learned by language models consistently exhibit striking geometric structure: calendar months organize into a circle, historical years form a smooth one-dimensional manifold, and cities' latitudes and longitudes can be decoded using a linear probe.

By Dhruva Karkada, Daniel J. Korchinski, Andres Nava, Matthieu Wyart, Yasaman Bahri

llms rag nlp

arXiv AI

Jul 1

JL1-CC&QA: Extending the JL1-CD Benchmark with Change Captioning and Question Answering

arXiv:2606. 31745v1 Announce Type: cross Abstract: Remote sensing change detection (CD) traditionally focuses on pixel-level binary segmentation, which identifies where changes occur but neither what nor why.

By Ziyuan Liu, Ruifei Zhu, Ouqiao Ma, Yuantao Gu

llms computer-vision nlp multimodal benchmarks

Get the daily briefing