Natural language processing

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

1,312 stories · RSS feed

arXiv Machine Learning

Aug 4

FAU at ImageCLEF 2026 Task on Multimodal Reasoning Robust Candidate Scoring and Concise Multilingual Visual Answering

arXiv:2608. 01664v1 Announce Type: cross Abstract: We present our ImageCLEF 2026 Multimodal Reasoning system for the Visual Multiple Choice Question Answering (Visual MCQ) and Visual Open Question Answering (Visual OpenQA) subtasks.

By Mohamed Basem, Vincent Christlein

llms nlp multimodal

arXiv Machine Learning

Aug 4

Just on Time: Token-Level Early Stopping for Diffusion Language Models

arXiv:2602. 11133v2 Announce Type: replace Abstract: Diffusion language models generate text through iterative refinement, a process that is often computationally inefficient because many tokens reach stability long before the final denoising step.

By Zakhar Kohut, Severyn Shykula, Mykola Vysotskyi, Serhii Dmytryshyn, Dmytro Khamula, Michal Zakrzewski, Damian Rynczak, Jacek Ma{\l}ecki, Taras Rumezhak, Volodymyr Karpiv

llms diffusion nlp fine-tuning benchmarks

arXiv Machine Learning

Aug 4

LiveMem: Maintaining Memory State Continuity in Long-Running LLM Inference

arXiv:2608. 02515v1 Announce Type: cross Abstract: Long-running assistants and agents consume interaction streams that eventually outgrow the context.

By Zhichen Liu, Ruihan Sun, Hengjie Yang, Zipeng Wu, Zhaohan Chen, Xiaofan Zhang, Yang Xu

llms agents nlp

arXiv Machine Learning

Aug 4

Slot2Text: Object-Centric Visual Tokenization for Efficient and Spatially Traceable Surgical MLLMs

arXiv:2608. 01473v1 Announce Type: cross Abstract: Multimodal large language models (MLLM) for surgical scene understanding typically inject hundreds of dense visual tokens into a language model, leading to costly inference and limited spatial traceability for generated answers.

By Guiqiu Liao, Matjaz Jogan, Daniel A. Hashimoto

llms nlp multimodal benchmarks safety

arXiv Machine Learning

Aug 4

Relative Parameter Importance in Task-Agnostic Replay-Free Continual Learning

arXiv:2608. 00630v1 Announce Type: new Abstract: Achieving continual learning (CL) with deep neural networks requires balancing stability and plasticity while enabling knowledge transfer.

By Malavika Suresh, Ikechukwu Nkisi-Orji, Nirmalie Wiratunga

nlp benchmarks

arXiv Machine Learning

Aug 4

Visualising Information Flow in Word Embeddings with Diffusion Tensor Imaging

arXiv:2601. 05713v2 Announce Type: replace-cross Abstract: Understanding how large language models (LLMs) represent natural language is a central challenge in natural language processing (NLP) research.

By Thomas Fabian

llms rag diffusion nlp efficiency safety

arXiv Machine Learning

Aug 4

EHR2Path: Comprehensive Pathway-Level Modeling of Longitudinal Patient Trajectories from Multimodal Electronic Health Records

arXiv:2506. 04831v3 Announce Type: replace Abstract: Forecasting how a patient's condition is likely to evolve, including possible deterioration, recovery, treatment needs, and care transitions, could support more proactive and personalized care, but requires modeling heterogeneous and longitudinal electronic health record (EHR) data.

By Chantal Pellegrini, Ege \"Ozsoy, David Bani-Harouni, Matthias Keicher, Nassir Navab

nlp multimodal

arXiv Machine Learning

Aug 4

MUSS: Multilevel Subset Selection for Relevance and Diversity

arXiv:2503. 11126v4 Announce Type: replace Abstract: The problem of relevant and diverse subset selection has a wide range of applications, including recommender systems and retrieval-augmented generation (RAG).

By Vu Nguyen, Andrey Kan

rag nlp

arXiv Machine Learning

Aug 4

OpenDebateEvidence: A Massive-Scale Argument Mining and Summarization Dataset

arXiv:2406. 14657v4 Announce Type: replace-cross Abstract: We introduce OpenDebateEvidence, a comprehensive dataset for argument mining and summarization sourced from the American Competitive Debate community.

By Allen Roush, Yusuf Shabazz, Arvind Balaji, Peter Zhang, Stefano Mezza, Markus Zhang, Sanjay Basu, Sriram Vishwanath, Mehdi Fatemi, Ravid Shwartz-Ziv

llms nlp fine-tuning benchmarks

arXiv Machine Learning

Aug 4

Scoring Rules! Statistical and Strategic Alignment for Text Evaluation Metrics

arXiv:2608. 01423v1 Announce Type: cross Abstract: Reference-based text evaluation metrics, which are widely used to assess natural language generation systems, score a candidate response by comparing it with a reference response.

By Shengwei Xu, Yuxuan Lu, Yifan Wu, Jason Hartline, Grant Schoenebeck

llms agents nlp robotics benchmarks safety

arXiv Machine Learning

Aug 4

TELLER: Non-intrusive Cross-Layer Root-Cause Analysis for LLM Inference

arXiv:2608. 01975v1 Announce Type: cross Abstract: Large language model (LLM) inference has evolved from an offline workload into a continuously operated software service, yet root-cause analysis remains difficult because a single request spans the inference engine, Python/C++ backend, host CUDA APIs, GPU kernels, and distributed communication.

By Ruilin Xu, Junyi Li, Pengfei Chen, Zongxuan Xie

llms nlp multimodal

arXiv Machine Learning

Aug 4

Agentic Graph Token Reasoning

arXiv:2608. 00542v1 Announce Type: new Abstract: Graphs model relational data throughout science and industry, from citation networks to product co-purchase graphs.

By Zhuoyi Peng, Yi Yang

llms agents nlp fine-tuning

arXiv Machine Learning

Aug 4

Automatic Annotation of Ancient Greek Vowel Length

arXiv:2608. 01935v1 Announce Type: cross Abstract: Prior work in Ancient Greek NLP relies on corpora that do not disambiguate the phonemic vowel length of alpha, iota, and ypsilon, together known as the dichrona.

By Albin Th\"orn Cleland, Eric Cullhed

llms nlp benchmarks

arXiv Machine Learning

Aug 4

Pruned BPE: Post-training Visibility Pruning and Token Reallocation for Byte Pair Encoding

arXiv:2608. 00837v1 Announce Type: cross Abstract: Byte Pair Encoding (BPE) is widely used for subword tokenization, but standard BPE exposes every learned merge token to the downstream model, including tokens that mainly serve as intermediate construction units and rarely appear in the final encoded corpus.

By Kenny Shao

llms nlp efficiency

arXiv Machine Learning

Aug 4

DRIFT: Drift-Resilient Invariant-Feature Transformer for DGA Detection

arXiv:2605. 10436v2 Announce Type: replace-cross Abstract: Domain Generation Algorithms (DGAs) evolve continuously to evade botnet detection, posing a persistent challenge for dependable network defense.

By Chaeyoung Lee, Chaeri Jung, Seonghoon Jeong

llms nlp fine-tuning benchmarks

arXiv Machine Learning

Aug 4

H+ Embedding: Harmonizing Global and Token-Level Retrieval with Context-Dependent Phrases

arXiv:2608. 00065v1 Announce Type: cross Abstract: Terminology-intensive retrieval, especially in medical settings, depends on preserving multi-word entities, abbreviations, numerical constraints, and compositional concepts.

By Shusen Zhang, Junyi Hu, Ye Feng, Ziteng Wang, Zhaoyuan Pan, Guosheng Dong, Xiaojun Yuan, Jiangshou Hong, Xiangzhi Wang

rag nlp

arXiv Machine Learning

Aug 4

T-TAMER: Provably Taming Trade-offs in ML Serving

arXiv:2509. 22992v2 Announce Type: replace Abstract: As machine learning models continue to grow in size and complexity, efficient serving faces increasingly broad trade-offs spanning accuracy, latency, resource usage, and other objectives.

By Yuanyuan Yang, Ruimin Zhang, Jamie Morgenstern, Haifeng Xu

nlp benchmarks

arXiv Machine Learning

Aug 4

3DZip: Spatial-Aware Feature Diversity-Guided Token Compression for 3D Question Answering

arXiv:2608. 01185v1 Announce Type: cross Abstract: Recent 3D vision-language models (3D VLMs) construct geometry aware tokens by projecting 2D visual features into world coordinates, enabling spatial reasoning for tasks such as 3D question answering.

By Changwoo Baek, Kyeongbo Kong

llms nlp efficiency multimodal benchmarks

Hugging Face Trending Papers

Aug 3

PhyCheck: Fine-Grained Evidence-Grounded Dataset for Physical Law Understanding in Video-LLMs

Embodied intelligence and world models require video understanding systems to go beyond recognizing objects and actions and develop an understanding of physical regularities. However, despite their strong performance on general video understanding tasks, current video-language models still struggle to reliably determine whether an observed event conforms to specific physical laws.

llms nlp robotics fine-tuning benchmarks

arXiv AI

Aug 3

Translation with Thought: Difficulty-Adaptive Reasoning via Reinforcement Learning for Multi-Domain Machine Translation

arXiv:2607. 29287v1 Announce Type: cross Abstract: Multi-domain machine translation (MDMT) poses a unique challenge due to varying levels of linguistic complexity across domains.

By Yongshi Ye, Biao Fu, Chongxuan Huang, Yidong Chen, Xiaodong Shi

llms nlp reinforcement-learning fine-tuning benchmarks