Related papers: Darkness Visible: Reading the Exception Handler of…

This study investigates the in-context learning capabilities of various decoder-only transformer-based language models with different model sizes and training data, including GPT2, SmolLM2, OpenELM, TinyLlama, Stable LM, and Gemma 2. We…

We introduce techniques for exploring the functionality of a neural network and extracting simple, human-readable approximations to its performance. By performing gradient ascent on the input space of the network, we are able to produce…

Recent studies have suggested a processing framework for multilingual inputs in decoder-based LLMs: early layers convert inputs into English-centric and language-agnostic representations; middle layers perform reasoning within an…

With the Generative Pre-trained Transformer 3.5 (GPT-3.5) exhibiting remarkable reasoning and comprehension abilities in Natural Language Processing (NLP), most Question Answering (QA) research has primarily centered around general QA tasks…

Objective: To develop a natural language processing (NLP) system to extract medications and contextual information that help understand drug changes. This project is part of the 2022 n2c2 challenge. Materials and methods: We developed NLP…

In this paper we propose a synergistic melting of neural networks and decision trees (DT) we call neural decision trees (NDT). NDT is an architecture a la decision tree where each splitting node is an independent multilayer perceptron…

A natural language parser which has been successfully implemented is described. This is a hybrid system, in which neural networks operate within a rule based framework. It can be accessed via telnet for users to try on their own text. (For…

Large Language Models (LLMs) are increasingly deployed in high-stakes financial domains, yet they suffer from specific, reproducible hallucinations when performing arithmetic operations. Current mitigation strategies often treat the model…

Existing prompting paradigms structure LLM reasoning in limited topologies: Chain-of-Thought (CoT) produces linear traces, while Tree-of-Thought (ToT) performs branching search. Yet complex reasoning often requires merging intermediate…

Explicit structural information has been proven to be encoded by Graph Neural Networks (GNNs), serving as auxiliary knowledge to enhance model capabilities and improve performance in downstream NLP tasks. However, recent studies indicate…

Recent developments in transformer-based language models have allowed them to capture a wide variety of world knowledge that can be adapted to downstream tasks with limited resources. However, what pieces of information are understood in…

Neural networks use their hidden layers to transform input data into linearly separable data clusters, with a linear or a perceptron type output layer making the final projection on the line perpendicular to the discriminating hyperplane.…

Multimodal language models (MLLMs) are increasingly paired with vision tools (e.g., depth, flow, correspondence) to enhance visual reasoning. However, despite access to these tool-generated visual cues, MLLMs often fail to benefit from…

The high-level concepts that a neural network uses to perform computation need not be aligned to individual neurons (Smolensky, 1986). Language model interpretability research has thus turned to techniques such as \textit{sparse…

Locating neurons that are responsible for final predictions is important for opening the black-box large language models and understanding the inside mechanisms. Previous studies have tried to find mechanisms that operate at the neuron…

Neural networks have greatly boosted performance in computer vision by learning powerful representations of input data. The drawback of end-to-end training for maximal overall performance are black-box models whose hidden representations…

While graph neural networks (GNNs) have shown remarkable performance across diverse graph-related tasks, their high-dimensional hidden representations render them black boxes. In this work, we propose Graph Lingual Network (GLN), a GNN…

When do transformers commit to a decision, and what prevents them from correcting it? We introduce \textbf{prolepsis}: a transformer commits early, task-specific attention heads sustain the commitment, and no layer corrects it. Replicating…

Recent advancements in large language models (LLMs) have shown promising results in multilingual translation even with limited bilingual supervision. The major challenges are catastrophic forgetting and parameter interference for finetuning…

While a lot of analysis has been carried to demonstrate linguistic knowledge captured by the representations learned within deep NLP models, very little attention has been paid towards individual neurons.We carry outa neuron-level analysis…