gsarti (Gabriele Sarti)

upvoted a paper about 6 hours ago

From Insights to Actions: The Impact of Interpretability and Analysis Research on NLP

Paper • 2406.12618 • Published 8 days ago • 4

upvoted a paper about 8 hours ago

Multi-property Steering of Large Language Models with Dynamic Activation Composition

Paper • 2406.17563 • Published 1 day ago • 1

upvoted a paper 1 day ago

Confidence Regulation Neurons in Language Models

Paper • 2406.16254 • Published 3 days ago • 7

upvoted a paper 5 days ago

Model Internals-based Answer Attribution for Trustworthy Retrieval-Augmented Generation

Paper • 2406.13663 • Published 7 days ago • 7

upvoted a paper 7 days ago

Estimating Knowledge in Large Language Models Without Generating a Single Token

Paper • 2406.12673 • Published 8 days ago • 6

upvoted a paper 9 days ago

Talking Heads: Understanding Inter-layer Communication in Transformer Language Models

Paper • 2406.09519 • Published 13 days ago • 1

upvoted a collection 19 days ago

Modello Italia - iGenius

Collection

An unofficial collection of Italian LLMs developed by iGenius. • 2 items • Updated 19 days ago • 6

upvoted a collection 20 days ago

IrokoBench

Collection

a human-translated benchmark dataset for 16 African languages covering three tasks: NLI, MMLU and MGSM • 6 items • Updated 26 days ago • 14

upvoted a paper 26 days ago

Calibrating Reasoning in Language Models with Internal Consistency

Paper • 2405.18711 • Published 29 days ago • 6

upvoted a paper 27 days ago

Emergence of a High-Dimensional Abstraction Phase in Language Transformers

Paper • 2405.15471 • Published May 24 • 2

upvoted a paper 29 days ago

From Neurons to Neutrons: A Case Study in Interpretability

Paper • 2405.17425 • Published 30 days ago • 2

upvoted 11 papers about 1 month ago

Learned feature representations are biased by complexity, learning order, position, and more

Paper • 2405.05847 • Published May 9 • 2

RAVEL: Evaluating Interpretability Methods on Disentangling Language Model Representations

Paper • 2402.17700 • Published Feb 27 • 1

Your Transformer is Secretly Linear

Paper • 2405.12250 • Published May 19 • 142

Interpretability Needs a New Paradigm

Paper • 2405.05386 • Published May 8 • 3

Sparse Autoencoders Enable Scalable and Reliable Circuit Identification in Language Models

Paper • 2405.12522 • Published May 21 • 2

Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning

Paper • 2405.12241 • Published May 17 • 1

The Local Interaction Basis: Identifying Computationally-Relevant and Sparsely Interacting Features in Neural Networks

Paper • 2405.10928 • Published May 17 • 1

Using Degeneracy in the Loss Landscape for Mechanistic Interpretability

Paper • 2405.10927 • Published May 17 • 2

Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control

Paper • 2405.08366 • Published May 14 • 2

Not All Language Model Features Are Linear

Paper • 2405.14860 • Published May 23 • 37

IT5: Large-scale Text-to-text Pretraining for Italian Language Understanding and Generation

Paper • 2203.03759 • Published Mar 7, 2022 • 5

upvoted a collection about 1 month ago

Wikimedia Datasets

Collection

Wikimedia datasets, across languages and modalities, from different Wikimedia projects, on the hub. Not all tested. • 19 items • Updated May 16 • 9

upvoted a collection about 2 months ago

WebLINX Models

Collection

https://mcgill-nlp.github.io/weblinx • 17 items • Updated 24 days ago • 6

upvoted 2 papers about 2 months ago

A Primer on the Inner Workings of Transformer-based Language Models

Paper • 2405.00208 • Published Apr 30 • 10

KAN: Kolmogorov-Arnold Networks

Paper • 2404.19756 • Published Apr 30 • 101

upvoted a paper 2 months ago

What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation

Paper • 2404.07129 • Published Apr 10 • 3

upvoted an article 2 months ago

Article

Vision Language Models Explained

Apr 11

• 110

upvoted a paper 2 months ago

LM Transparency Tool: Interactive Tool for Analyzing Transformer Language Models

Paper • 2404.07004 • Published Apr 10 • 5

upvoted 2 collections 2 months ago

Idefics2 🐶

Collection

Idefics2-8B is a foundation vision-language model. In this collection, you will find the models, datasets and demo related to its creation. • 11 items • Updated May 6 • 85

Pile-T5

Collection

T5 trained on the Pile with Llama Tokenizer • 5 items • Updated 13 days ago • 16

upvoted 2 papers 3 months ago

Locating and Editing Factual Associations in Mamba

Paper • 2404.03646 • Published Apr 4 • 3

Does Transformer Interpretability Transfer to RNNs?

Paper • 2404.05971 • Published Apr 9 • 3

upvoted an article 3 months ago

Article

Analysis on evaluating 7 bilions italian LLMs

By

•

Apr 10

• 2

upvoted a collection 3 months ago

Italian Sentence Transformers

Collection

11 items • Updated Feb 23 • 3

upvoted 3 papers 3 months ago

upvoted 2 collections 3 months ago

Zeroshot Classifiers

Collection

These are my current best zeroshot classifiers. Some of my older models are downloaded more often, but the models in this collection are newer/better. • 11 items • Updated Apr 3 • 83

A little guide to building Large Language Models in 2024

Collection

Resources mentioned by @thomwolf in https://x.com/Thom_Wolf/status/1773340316835131757 • 19 items • Updated Apr 1 • 14

upvoted 3 papers 3 months ago

Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models

Paper • 2403.19647 • Published Mar 28 • 3

Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanisms

Paper • 2403.17806 • Published Mar 26 • 3

DecoderLens: Layerwise Interpretation of Encoder-Decoder Transformers

Paper • 2310.03686 • Published Oct 5, 2023 • 3

upvoted 3 papers 4 months ago

DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models

Paper • 2309.03883 • Published Sep 7, 2023 • 14

Information Flow Routes: Automatically Interpreting Language Models at Scale

Paper • 2403.00824 • Published Feb 27 • 3

AtP*: An efficient and scalable method for localizing LLM behaviour to components

Paper • 2403.00745 • Published Mar 1 • 8

upvoted a collection 4 months ago

LiT5

Collection

Linguistically-Informed T5 models from the LREC-COLING paper "Linguistic Knowledge Can Enhance Encoder-Decoder Models (If You Let It)". • 6 items • Updated Feb 28 • 2

upvoted 5 papers 4 months ago

CausalGym: Benchmarking causal interpretability methods on linguistic tasks

Paper • 2402.12560 • Published Feb 19 • 3

Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking

Paper • 2402.14811 • Published Feb 22 • 4

Enhanced Hallucination Detection in Neural Machine Translation through Simple Detector Aggregation

Paper • 2402.13331 • Published Feb 20 • 2

Backward Lens: Projecting Language Model Gradients into the Vocabulary Space

Paper • 2402.12865 • Published Feb 20 • 1

In-Context Learning Demonstration Selection via Influence Analysis

Paper • 2402.11750 • Published Feb 19 • 2

upvoted a collection 4 months ago

⛔️🔦 Provenance, Watermarking & Deepfake Detection

Collection

Technical tools for more control over non-consensual synthetic content • 14 items • Updated Apr 1 • 37

upvoted 3 papers 4 months ago

Recovering the Pre-Fine-Tuning Weights of Generative Models

Paper • 2402.10208 • Published Feb 15 • 6

SyntaxShap: Syntax-aware Explainability Method for Text Generation

Paper • 2402.09259 • Published Feb 14 • 2

Show Me How It's Done: The Role of Explanations in Fine-Tuning Language Models

Paper • 2402.07543 • Published Feb 12 • 2

upvoted a collection 4 months ago

LLM Hallucination Detection Papers

Collection

Collection of LLM hallucination and evaluation papers that I've been exploring and implementing. Some of them have my comments and annotated doodles. • 12 items • Updated Feb 20 • 12

upvoted 3 papers 5 months ago

Model Editing with Canonical Examples

Paper • 2402.06155 • Published Feb 9 • 10

AttnLRP: Attention-Aware Layer-wise Relevance Propagation for Transformers

Paper • 2402.05602 • Published Feb 8 • 3

Faithfulness vs. Plausibility: On the (Un)Reliability of Explanations from Large Language Models

Paper • 2402.04614 • Published Feb 7 • 3

Gabriele Sarti

AI & ML interests

Organizations

gsarti's activity

Vision Language Models Explained

Analysis on evaluating 7 bilions italian LLMs