Natural language processing

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

2,641 stories · RSS feed

arXiv AI

Aug 21

Question-Guided Evidence Acquisition for Multimodal Visual Question Answering

arXiv:2608. 19739v1 Announce Type: cross Abstract: Multimodal LLMs can see a document, but they often can't read it reliably.

By Alin-Ionut Popa

llms agents nlp multimodal

arXiv AI

Aug 21

Task-CoEvolve: Efficient Harness Optimization via Adaptive Validation Task Selection

arXiv:2608. 20169v1 Announce Type: cross Abstract: We present a novel approach to efficient LLM agent harness optimization through adaptive validation task selection.

By Atsuyuki Miyai, Kiyoharu Aizawa, Toshihiko Yamasaki

llms agents nlp

arXiv Computation and Language

Aug 21

Robust Incomplete Multimodal Sentiment Analysis via Iterative Proxy Correction

arXiv:2608. 19971v1 Announce Type: new Abstract: Multimodal sentiment analysis aims to infer affective states by integrating language, visual, and acoustic cues.

By Zhifa Geng, Subin Huang, Hao Guo, Junjie Chen, Sanmin Liu, Chao Kong

nlp multimodal

arXiv AI

Aug 21

Automatic bioinformatic software named entity recognition from literature

arXiv:2608. 19201v1 Announce Type: cross Abstract: Bioinformatics software and databases are essential components of modern life science research, yet their mentions in the scientific literature are often inconsistent and difficult to systematically identify at scale.

By Hao Xuan, Rithvij Pasupuleti, Ben Liu, Haishuo Sun, Jun Zhang, Zijun Yao, Cuncong Zhong

llms rag nlp efficiency benchmarks

arXiv Computation and Language

Aug 21

Reliable Financial Named Entity Recognition under Domain Shift

arXiv:2608. 19558v1 Announce Type: new Abstract: Financial AI systems often train information extractors on one textual register and deploy them across filings, news, and user-generated content, while standard F1 scores do not indicate which predictions remain safe to automate when the input distribution changes.

By Zihao Zheng, Baichuan Li, Junyi Yao, Jiayu Long

nlp fine-tuning

arXiv Machine Learning

Aug 21

Holtercare-Bench: A Multimodal Benchmark for Evaluating Long-Term Dynamic ECG Analysis

arXiv:2608. 19297v1 Announce Type: new Abstract: While multimodal large language models (MLLMs) excel in medical applications, most of them favor static images or short-term signals.

By Yihan Xie, Hanwen Cui, Runze Ye, Juekai Lin, Haoyang Wang, Jinhao Mao, Bo Zhang, Wenqiao Zhang, Xiaogang Guo, Jun Xiao, Lei Zhang

llms nlp fine-tuning multimodal benchmarks safety

arXiv Computer Vision

Aug 21

Exploiting Completeness Perception with Diffusion Transformer for Unified 3D MRI Synthesis

arXiv:2602. 18400v3 Announce Type: replace-cross Abstract: Missing data problems, such as missing modalities in multi-modal brain MRI and missing slices in cardiac MRI, pose significant challenges in clinical practice.

By Junkai Liu, Nay Aung, Theodoros N. Arvanitis, Joao A. C. Lima, Steffen E. Petersen, Le Zhang

llms diffusion nlp multimodal benchmarks

arXiv Machine Learning

Aug 21

Decoupling High and Low Frequencies for Faithful Image Generation with Fine Details

arXiv:2509. 05441v4 Announce Type: replace-cross Abstract: Latent generative models compress images into learned embeddings prior to synthesis, and the generation quality critically depends on how faithfully these embeddings preserve visual detail.

By Tejaswini Medi, Hsien-Yi Wang, Arianna Rampini, Margret Keuper

rag diffusion nlp

arXiv Machine Learning

Aug 21

CarBench: A Comprehensive Benchmark for Neural Surrogates on High-Fidelity 3D Car Aerodynamics

arXiv:2512. 07847v2 Announce Type: replace Abstract: Benchmarking has been the cornerstone of progress in computer vision, natural language processing, and the broader deep learning domain, driving algorithmic innovation through standardized datasets and reproducible evaluation protocols.

By Mohamed Elrefaie, Dule Shu, Matt Klenk, Faez Ahmed

llms computer-vision nlp benchmarks

arXiv Computer Vision

Aug 21

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation

arXiv:2607. 14497v2 Announce Type: replace Abstract: Egocentric Visual Question Answering (VQA) has attracted widespread attention as an important task for enabling Multimodal Large Language Models (MLLMs) to interact with the real world.

By Chi Kit Wong, Ye Pan, Yuanhuiyi Lyu, Xu Zheng, Zidong Cao, Lutao Jiang, Zixin Zhang, Huiyu Zhou, Xuming Hu

llms nlp multimodal benchmarks

arXiv Computation and Language

Aug 21

Stopping and Routing LLM Judge Panels

arXiv:2608. 19802v1 Announce Type: new Abstract: LLM evaluation pipelines often have many candidate judges: general LLM-as-a-judge prompts, reward models, safety classifiers, confidence variants, and task-specific verifiers.

By Bin Zhu, Yi Xie, Yanghui Rao

llms nlp safety

arXiv Computation and Language

Aug 21

GreekBarRetrieval: A Benchmark for Greek Statutory Retrieval

arXiv:2608. 18752v2 Announce Type: replace-cross Abstract: Statutory retrieval is necessary for citation-grounded legal question answering, but remains underexplored for Greek.

By Ernest Beta, Odysseas S. Chlapanis, Dimitrios Galanis, Ion Androutsopoulos

llms nlp benchmarks

arXiv Computation and Language

Aug 21

Doc-V*:Coarse-to-Fine Interactive Visual Reasoning for Multi-Page Document VQA

arXiv:2604. 13731v2 Announce Type: replace Abstract: Multi-page Document Visual Question Answering requires reasoning over semantics, layouts, and visual elements in long, visually dense documents.

By Yuanlei Zheng, Pei Fu, Hang Li, Ziyang Wang, Yuyi Zhang, Wenyu Ruan, Xiaojin Zhang, Zhongyu Wei, Zhenbo Luo, Jian Luan, Wei Chen, Xiang Bai

rag agents computer-vision nlp benchmarks

arXiv Computation and Language

Aug 21

ReCache: Efficient KV Cache Reuse and Compression for Tool-Augmented LLM Agents

arXiv:2608. 19662v1 Announce Type: new Abstract: Agentic language models repeatedly encode tool and skill schemas that recur across requests in different combinations and orders, preventing standard prefix caching from reusing their key--value (KV) states.

By Yichu Fang, Sitong Wei, Haozhe Hu, Xiaoyu Shen

llms agents nlp efficiency benchmarks

arXiv AI

Aug 21

Inject, Align, Recover: Staged Post-Training for Retrieval-Free Document Knowledge Internalization

arXiv:2608. 20281v1 Announce Type: cross Abstract: Large language models often fail to answer questions about a bounded document collection when the source documents are not retrieved at inference time.

By Qian Kou, Xiaofeng Shi, Xiaosong Qiu, Hua Zhou

llms nlp fine-tuning benchmarks safety

arXiv AI

Aug 21

ContractScrub: A benchmark for final review of legal contracts

arXiv:2608. 20204v1 Announce Type: new Abstract: Legal work, with its heavy reliance on processing large amounts of text, is often considered one of the domains most exposed to the use of LLMs.

By Yejin Bang, Kirsty Fielding, Brandan Oliver, Brian Birke, Nabeel Seedat, Andrew M. Bean

llms nlp benchmarks

arXiv Computation and Language

Aug 21

Explainable Multimodal Depression Recognition in Clinical Interviews via PHQ-Aligned Symptom Summarization

arXiv:2501. 16106v2 Announce Type: replace Abstract: Recent advances in multimodal depression recognition for clinical interviews (MDRC) have demonstrated the potential of AI systems by integrating textual, acoustic, and facial cues.

By Wenjie Zheng, Qiming Xie, Jianfei Yu, Yang Wang, Lei Cao, Fei Wang, Shijin Wang, Rui Xia, Chengqing Zong

nlp multimodal safety

arXiv Computer Vision

Aug 21

ArmorOCR: Grounded Adversarial Visual Perception via Observation-Transferred Self-Distillation

arXiv:2608. 20122v1 Announce Type: new Abstract: Large multimodal models (LMMs) have demonstrated strong OCR recognition capabilities, yet remain vulnerable to adversarial visual text that is readable to humans but challenging for models to localize and recognize.

By Linhan Cao, Siyuan Li, Jun Lan, Liangbo He, Guannan Li, Xiaolei Huang, Jun Jia, Shuheng Zhou, Huijia Zhu, Weiqiang Wang, Wei Sun

computer-vision nlp efficiency multimodal benchmarks safety

arXiv AI

Aug 21

Automated Summarization of Financial News Using Large Language Models and Retrieval-Augmented Generation: An Early Empirical Study (Fall 2023)

arXiv:2608. 19526v1 Announce Type: cross Abstract: Stock market analysts and investors face a daily challenge: too much financial news, too little time.

By Pranav Chandaliya

llms rag nlp safety

arXiv Computation and Language

Aug 21

Natural Language Code Retrieval for 1C:Enterprise: An Open Benchmark and Efficient Bi-Encoder

arXiv:2608. 19957v1 Announce Type: new Abstract: Natural language code retrieval is a rapidly evolving task in computer science.

By Konstantin Chesnokov, Chingiz Mingazov

nlp fine-tuning benchmarks safety

Get the daily briefing