Natural Language Processing

Text understanding and language tasks

This Week's Best | Monthly Best | Guide | Trending

Top This Week

[2602.00750] Bypassing Prompt Injection Detectors through Evasive Injections
Llms

[2602.00750] Bypassing Prompt Injection Detectors through Evasive Injections

Abstract page for arXiv paper 2602.00750: Bypassing Prompt Injection Detectors through Evasive Injections

arXiv - AI · 4 min ·
[2512.18640] Geometric-Photometric Event-based 3D Gaussian Ray Tracing
Nlp

[2512.18640] Geometric-Photometric Event-based 3D Gaussian Ray Tracing

Abstract page for arXiv paper 2512.18640: Geometric-Photometric Event-based 3D Gaussian Ray Tracing

arXiv - AI · 4 min ·
[2511.08225] Benchmarking Educational LLMs with Analytics: A Case Study on Gender Bias in Feedback
Llms

[2511.08225] Benchmarking Educational LLMs with Analytics: A Case Study on Gender Bias in Feedback

Abstract page for arXiv paper 2511.08225: Benchmarking Educational LLMs with Analytics: A Case Study on Gender Bias in Feedback

arXiv - AI · 4 min ·

All Content

[2602.22895] SPD Learn: A Geometric Deep Learning Python Library for Neural Decoding Through Trivialization
Machine Learning

[2602.22895] SPD Learn: A Geometric Deep Learning Python Library for Neural Decoding Through Trivialization

SPD Learn is a new Python library designed for geometric deep learning, specifically for neural decoding using symmetric positive definit...

arXiv - Machine Learning · 3 min ·
[2602.22678] ViCLIP-OT: The First Foundation Vision-Language Model for Vietnamese Image-Text Retrieval with Optimal Transport
Llms

[2602.22678] ViCLIP-OT: The First Foundation Vision-Language Model for Vietnamese Image-Text Retrieval with Optimal Transport

ViCLIP-OT introduces a novel vision-language model tailored for Vietnamese image-text retrieval, outperforming existing models in low-res...

arXiv - AI · 4 min ·
[2602.22827] TARAZ: Persian Short-Answer Question Benchmark for Cultural Evaluation of Language Models
Llms

[2602.22827] TARAZ: Persian Short-Answer Question Benchmark for Cultural Evaluation of Language Models

The paper presents TARAZ, a Persian short-answer question benchmark designed to evaluate the cultural competence of large language models...

arXiv - Machine Learning · 3 min ·
[2602.22606] CoLyricist: Enhancing Lyric Writing with AI through Workflow-Aligned Support
Generative Ai

[2602.22606] CoLyricist: Enhancing Lyric Writing with AI through Workflow-Aligned Support

CoLyricist is an AI-assisted tool designed to enhance the lyric writing process by aligning with the common workflows of lyricists, impro...

arXiv - AI · 3 min ·
[2602.22596] BetterScene: 3D Scene Synthesis with Representation-Aligned Generative Model
Machine Learning

[2602.22596] BetterScene: 3D Scene Synthesis with Representation-Aligned Generative Model

BetterScene introduces an innovative approach to 3D scene synthesis, enhancing novel view synthesis quality using sparse photos and a rep...

arXiv - AI · 4 min ·
[2602.22661] dLLM: Simple Diffusion Language Modeling
Llms

[2602.22661] dLLM: Simple Diffusion Language Modeling

The paper introduces dLLM, an open-source framework for diffusion language modeling that standardizes core components, facilitating repro...

arXiv - Machine Learning · 3 min ·
[2602.22647] Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators
Llms

[2602.22647] Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators

The paper presents STATIC, a novel approach for efficient constrained decoding in LLM-based generative retrieval, significantly enhancing...

arXiv - Machine Learning · 4 min ·
[2602.22576] Search-P1: Path-Centric Reward Shaping for Stable and Efficient Agentic RAG Training
Llms

[2602.22576] Search-P1: Path-Centric Reward Shaping for Stable and Efficient Agentic RAG Training

The paper presents Search-P1, a framework for enhancing Retrieval-Augmented Generation (RAG) training through path-centric reward shaping...

arXiv - Machine Learning · 3 min ·
[2602.22551] A Fast and Practical Column Generation Approach for Identifying Carcinogenic Multi-Hit Gene Combinations
Nlp

[2602.22551] A Fast and Practical Column Generation Approach for Identifying Carcinogenic Multi-Hit Gene Combinations

This paper presents a novel approach to identifying carcinogenic multi-hit gene combinations using a fast column generation method, signi...

arXiv - Machine Learning · 3 min ·
[2602.22547] Towards Dynamic Dense Retrieval with Routing Strategy
Machine Learning

[2602.22547] Towards Dynamic Dense Retrieval with Routing Strategy

The paper presents a novel approach to dense retrieval called Dynamic Dense Retrieval (DDR), which addresses limitations in adapting mode...

arXiv - Machine Learning · 4 min ·
[2602.22524] Iterative Prompt Refinement for Dyslexia-Friendly Text Summarization Using GPT-4o
Llms

[2602.22524] Iterative Prompt Refinement for Dyslexia-Friendly Text Summarization Using GPT-4o

This paper explores an iterative prompt refinement method for creating dyslexia-friendly text summaries using GPT-4o, demonstrating impro...

arXiv - AI · 3 min ·
[2602.22522] Efficient Dialect-Aware Modeling and Conditioning for Low-Resource Taiwanese Hakka Speech Processing
Machine Learning

[2602.22522] Efficient Dialect-Aware Modeling and Conditioning for Low-Resource Taiwanese Hakka Speech Processing

This article presents a novel framework for improving automatic speech recognition (ASR) for the low-resource Taiwanese Hakka language by...

arXiv - AI · 4 min ·
[2602.22483] Importance of Prompt Optimisation for Error Detection in Medical Notes Using Language Models
Llms

[2602.22483] Importance of Prompt Optimisation for Error Detection in Medical Notes Using Language Models

This paper discusses the significance of prompt optimization in enhancing error detection in medical notes using language models, demonst...

arXiv - AI · 3 min ·
[2602.22456] Automating the Detection of Requirement Dependencies Using Large Language Models
Llms

[2602.22456] Automating the Detection of Requirement Dependencies Using Large Language Models

This article presents LEREDD, a novel approach utilizing Large Language Models to automate the detection of requirement dependencies in s...

arXiv - AI · 4 min ·
[2602.22449] A Fusion of context-aware based BanglaBERT and Two-Layer Stacked LSTM Framework for Multi-Label Cyberbullying Detection
Nlp

[2602.22449] A Fusion of context-aware based BanglaBERT and Two-Layer Stacked LSTM Framework for Multi-Label Cyberbullying Detection

This paper presents a novel framework combining BanglaBERT and a two-layer stacked LSTM for effective multi-label cyberbullying detection...

arXiv - Machine Learning · 4 min ·
[2602.22432] LoBoost: Fast Model-Native Local Conformal Prediction for Gradient-Boosted Trees
Machine Learning

[2602.22432] LoBoost: Fast Model-Native Local Conformal Prediction for Gradient-Boosted Trees

LoBoost introduces a novel method for local conformal prediction in gradient-boosted trees, enhancing uncertainty quantification without ...

arXiv - Machine Learning · 3 min ·
[2602.22434] GetBatch: Distributed Multi-Object Retrieval for ML Data Loading
Machine Learning

[2602.22434] GetBatch: Distributed Multi-Object Retrieval for ML Data Loading

GetBatch introduces a new object store API that enhances batch retrieval in machine learning data loading, achieving significant performa...

arXiv - Machine Learning · 3 min ·
[2602.22427] HubScan: Detecting Hubness Poisoning in Retrieval-Augmented Generation Systems
Llms

[2602.22427] HubScan: Detecting Hubness Poisoning in Retrieval-Augmented Generation Systems

The paper presents HubScan, a tool designed to detect hubness poisoning in Retrieval-Augmented Generation systems, addressing a critical ...

arXiv - AI · 4 min ·
[2602.22426] SimpleOCR: Rendering Visualized Questions to Teach MLLMs to Read
Llms

[2602.22426] SimpleOCR: Rendering Visualized Questions to Teach MLLMs to Read

The paper introduces SimpleOCR, a method to enhance Multimodal Large Language Models (MLLMs) by rendering visualized questions, addressin...

arXiv - Machine Learning · 4 min ·
[2602.22424] Causality $\neq$ Invariance: Function and Concept Vectors in LLMs
Llms

[2602.22424] Causality $\neq$ Invariance: Function and Concept Vectors in LLMs

This paper investigates the representation of concepts in large language models (LLMs), revealing that Function Vectors (FVs) are not ful...

arXiv - Machine Learning · 4 min ·
Previous Page 68 Next

Related Topics

Machine Learning Large Language Models Generative AI Computer Vision Robotics & Embodied AI AI Safety & Ethics

Stay updated with AI News

Get the latest news, tools, and insights delivered to your inbox.

Subscribe to Newsletter

Daily or weekly digest • Unsubscribe anytime