Interpreting Language Models Through Knowledge Graph Extraction

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

The ability to reason, plan and solve highly abstract problems is a hallmark of human intelligence. Recent advancements in artificial intelligence, propelled by deep neural networks, have revolutionized disciplines like computer vision and natural language ...

Large language models (LLMs) have shown strong performance in tasks across domains but struggle with chemistry-related problems. These models also lack access to external knowledge sources, limiting their usefulness in scientific applications. We introduce ...

Transformer models such as GPT generate human-like language and are predictive of human brain responses to language. Here, using functional-MRI-measured brain responses to 1,000 diverse sentences, we first show that a GPT-based encoding model can predict t ...

Cell segmentation is a critical step for quantitative single-cell analysis in microscopy images. Existing cell segmentation methods are often tailored to specific modalities or require manual interventions to specify hyper-parameters in different experimen ...

Traditional martial arts are treasures of humanity's knowledge and critical carriers of sociocultural memories throughout history. However, such treasured practices have encountered various challenges in knowledge transmission and now feature many entries ...

Under resource constraints, LLMs are usually fine- tuned with additional knowledge using Parameter Efficient Fine-Tuning (PEFT), using Low-Rank Adaptation (LoRA) modules. In fact, LoRA injects a new set of small trainable matrices to adapt an LLM to a new ...

Under resource constraints, LLMs are usually fine-tuned with additional knowledge using Parameter Efficient Fine-Tuning (PEFT), using Low-Rank Adaptation (LoRA) modules. In fact, LoRA injects a new set of small trainable matrices to adapt an LLM to a new t ...

Accurate human trajectory prediction is crucial for applications such as autonomous vehicles, robotics, and surveillance systems. Yet, existing models often fail to fully leverage the non-verbal social cues human subconsciously communicate when navigating ...

Designing novel materials is greatly dependent on understanding the design principles, physical mechanisms, and modeling methods of material microstructures, requiring experienced designers with expertise and several rounds of trial and error. Although rec ...

Generative language models (LMs) have become omnipresent across data science. For a wide variety of tasks, inputs can be phrased as natural language prompts for an LM, from whose output the solution can then be extracted. LM performance has consistently be ...

In the rapidly evolving landscape of machine learning research, neural networks stand out with their ever-expanding number of parameters and reliance on increasingly large datasets. The financial cost and computational resources required for the training p ...

Modern neuroscience research is generating increasingly large datasets, from recording thousands of neurons over long timescales to behavioral recordings of animals spanning weeks, months, or even years. Despite a great variety in recording setups and expe ...

Recent advancements in deep learning have revolutionized 3D computer vision, enabling the extraction of intricate 3D information from 2D images and video sequences. This thesis explores the application of deep learning in three crucial challenges of 3D com ...

Adversarial attacks in Natural Language Processing apply perturbations in the character or token levels. Token-level attacks, gaining prominence for their use of gradient-based methods, are susceptible to altering sentence semantics, leading to invalid adv ...

It is of great interest to the energy community to understand how the mechano-physico-chemical phenomena that eventually lead to device degradation are related to the startup, operation, and shutdown phases. For electrocatalytic systems operating in liquid ...

The field of biometrics, and especially face recognition, has seen a wide-spread adoption the last few years, from access control on personal devices such as phones and laptops, to automated border controls such as in airports. The stakes are increasingly ...

Machine learning (ML) enables artificial intelligent (AI) agents to learn autonomously from data obtained from their environment to perform tasks. Modern ML systems have proven to be extremely effective, reaching or even exceeding human intelligence. Altho ...

In this dissertation, we propose multiple methods to improve transfer learning for pretrained language models (PLMs). Broadly, transfer learning is a powerful technique in natural language processing, where a language model is first pre-trained on a data-r ...

Natural language processing has experienced significant improvements with the development of Transformer-based models, which employ self-attention mechanism and pre-training strategies. However, these models still present several obstacles. A notable issue ...

Abstractive summarization has seen big improvements in recent years, mostly due to advances in neural language modeling, language model pretraining, and scaling models and datasets. While large language models generate summaries that are fluent, coherent, ...

Interpreting Language Models Through Knowledge Graph Extraction

Chat with Graph Search

Infusing structured knowledge priors in neural models for sample-efficient symbolic reasoning

Augmenting large language models with chemistry tools

Driving and suppressing the human language network using large language models

The multimodality cell segmentation challenge: toward universal solutions

Ontology-based Knowledge Representation for Traditional Martial Arts

Beyond fine-tuning: LoRA modules boost near-OOD detection and LLM security

Beyond fine-tuning: LoRA modules boost near-OOD detection and LLM security

Social-Transmotion: Promptable Human Trajectory Prediction

Text-to-Microstructure Generation Using Generative Deep Learning

Fly-Swat or Cannon? Cost-Effective Language Model Choice via Meta-Modeling

Random matrix methods for high-dimensional machine learning models

Robust machine learning for neuroscientific inference

Advancing Self-Supervised Deep Learning for 3D Scene Understanding

Revisiting Character-level Adversarial Attacks for Language Models

Quasi-operando Transmission Electron Microscopy Diagnostics for Electrocatalytic Processes in Liquids

Performing and Detecting Backdoor Attacks on Face Recognition Algorithms

Few-shot Learning for Efficient and Effective Machine Learning Model Adaptation

Improving Generalization of Pretrained Language Models

Modeling Structured Data in Attention-based Models

Interpretable Representation Learning and Evaluation for Abstractive Summarization