Imagen de Portada

InTraVisTo: Inside Transformer Visualisation Tool

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Brunello, Nicolò, Rigamonti, Davide, Sassella, Andrea, Scotti, Vincenzo, Carman, Mark James
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

From Instructions to Assistance: a Dataset Aligning Instruction Manuals with Assembly Videos for Evaluating Multimodal LLMs
por: Toschi, Federico, et al.
Publicado: (2026)

L1RA: Dynamic Rank Assignment in LoRA Fine-Tuning
por: Singh, Raul, et al.
Publicado: (2025)

Are complicated loss functions necessary for teaching LLMs to reason?
por: Carrino, Gabriele, et al.
Publicado: (2026)

Benchmarking EngGPT2-16B-A3B against Comparable Italian and International Open-source LLMs
por: Sassella, Andrea, et al.
Publicado: (2026)

Do Text-to-Vis Benchmarks Test Real Use of Visualisations?
por: Nguyen, Hy, et al.
Publicado: (2024)

More Church-Rosser Proofs in BELUGA
por: Momigliano, Alberto, et al.
Publicado: (2024)

A Shared Geometry of Difficulty in Multilingual Language Models
por: Civelli, Stefano, et al.
Publicado: (2026)

Expect the unexpected: Harnessing Sentence Completion for Sarcasm Detection
por: Joshi, Aditya, et al.
Publicado: (2017)

ReasonGraph: Visualisation of Reasoning Paths
por: Li, Zongqian, et al.
Publicado: (2025)

SumTra: A Differentiable Pipeline for Few-Shot Cross-Lingual Summarization
por: Parnell, Jacob, et al.
Publicado: (2024)

Automata-less Monitoring via Trace-Checking (Extended Version)
por: Brunello, Andrea, et al.
Publicado: (2025)

Do LLMs Really Struggle at NL-FOL Translation? Revealing their Strengths via a Novel Benchmarking Strategy
por: Brunello, Andrea, et al.
Publicado: (2025)

Do You Understand How I Feel?: Towards Verified Empathy in Therapy Chatbots
por: Dettori, Francesco, et al.
Publicado: (2026)

LM Transparency Tool: Interactive Tool for Analyzing Transformer Language Models
por: Tufanov, Igor, et al.
Publicado: (2024)

Visualising Policy-Reward Interplay to Inform Zeroth-Order Preference Optimisation of Large Language Models
por: Galatolo, Alessio, et al.
Publicado: (2025)

VisTIRA: Closing the Image-Text Modality Gap in Visual Math Reasoning via Structured Tool Integration
por: Khaki, Saeed, et al.
Publicado: (2026)

DeVisE: Behavioral Testing of Medical Large Language Models
por: Tagliabue, Camila Zurdo, et al.
Publicado: (2025)

VisTW: Benchmarking Vision-Language Models for Traditional Chinese in Taiwan
por: Tam, Zhi Rui, et al.
Publicado: (2025)

How Toxic Can You Get? Search-based Toxicity Testing for Large Language Models
por: Corbo, Simone, et al.
Publicado: (2025)

Visualising Information Flow in Word Embeddings with Diffusion Tensor Imaging
por: Fabian, Thomas
Publicado: (2026)

Interpretable Early Failure Detection via Machine Learning and Trace Checking-based Monitoring
por: Brunello, Andrea, et al.
Publicado: (2025)

On the Universal Truthfulness Hyperplane Inside LLMs
por: Liu, Junteng, et al.
Publicado: (2024)

VisMin: Visual Minimal-Change Understanding
por: Awal, Rabiul, et al.
Publicado: (2024)

Text-to-TrajVis: Enabling Trajectory Data Visualizations from Natural Language Questions
por: Bai, Tian, et al.
Publicado: (2025)

OmniThoughtVis: A Scalable Distillation Pipeline for Deployable Multimodal Reasoning Models
por: Yue, Yuanhao, et al.
Publicado: (2026)

Toolshed: Scale Tool-Equipped Agents with Advanced RAG-Tool Fusion and Tool Knowledge Bases
por: Lumer, Elias, et al.
Publicado: (2024)

Finite State Automata Inside Transformers with Chain-of-Thought: A Mechanistic Study on State Tracking
por: Zhang, Yifan, et al.
Publicado: (2025)

VisCoder2: Building Multi-Language Visualization Coding Agents
por: Ni, Yuansheng, et al.
Publicado: (2025)

Visualising CTL Witnesses and Counterexamples -- Extended Version
por: Rensink, Arend
Publicado: (2026)

A2P-Vis: an Analyzer-to-Presenter Agentic Pipeline for Visual Insights Generation and Reporting
por: Gan, Shuyu, et al.
Publicado: (2025)

VisEval: A Benchmark for Data Visualization in the Era of Large Language Models
por: Chen, Nan, et al.
Publicado: (2024)

Inside-Out: Hidden Factual Knowledge in LLMs
por: Gekhman, Zorik, et al.
Publicado: (2025)

VisRet: Visualization Improves Knowledge-Intensive Text-to-Image Retrieval
por: Wu, Di, et al.
Publicado: (2025)

A Directed Graph Model and Experimental Framework for Design and Study of Time-Dependent Text Visualisation
por: Fan, Songhai, et al.
Publicado: (2026)

VisJudge-Bench: Aesthetics and Quality Assessment of Visualizations
por: Xie, Yupeng, et al.
Publicado: (2025)

Annotation Tool and Dataset for Fact-Checking Podcasts
por: Setty, Vinay, et al.
Publicado: (2025)

Thinking Inside the Mask: In-Place Prompting in Diffusion LLMs
por: Jin, Xiangqi, et al.
Publicado: (2025)

Reasoning Gets Harder for LLMs Inside A Dialogue
por: Kartáč, Ivan, et al.
Publicado: (2026)

From scratch to silver: Creating trustworthy training data for patent-SDG classification using Large Language Models
por: Ascione, Grazia Sveva, et al.
Publicado: (2025)

VisBias: Measuring Explicit and Implicit Social Biases in Vision Language Models
por: Huang, Jen-tse, et al.
Publicado: (2025)