Aryaman Arora

CausalGym: Benchmarking causal interpretability methods on linguistic tasks

Bayesian scaling laws for in-context learning.

Code for the ACL 2020 Paper on Schwa Deletion in Hindi and Punjabi

Framework for performing mechanistic evaluations of language model architectures on synthetic tasks

D3.js visualization of the language parts of the 2011 Census of India.

Programming contests practice and solutions. Includes solutions to problems from USACO training pages, Codeforces, Codechef, and other online judges. Mainly C++.

A coronavirus map for the U.S. made with d3.js.

Extremely simple implementation of path patching (aka causal scrubbing) in PyTorch.

Map of South Asian language resources, and areal features.

prime-rl is a codebase for decentralized RL training at scale

Various G2P scripts for Bengali (incl. data from https://dsal.uchicago.edu/dictionaries/bhattacharya/).

Induction heads

Hindi SNACS (Semantic Network of Adposition and Case Supersenses; Schneider et al., 2018) annotation scheme and guidelines.

A diabetes predictor website that uses the UCI Pima Indians Diabetes Database and some machine learning.

Tool for automatically doing scansion of Urdu poetry.

A language and linguistics resources list.

FBLA Coding and Programming

Coursework and notes for Harvard's online course CS50x: Introduction to Computer Science, 2017 session.

Dumb neural networks that play connect four. Natural selection finds the best of the worst bots.

An application for storing memories in a semantic database.

A map of my family's travels, forked from jlfwong/travelmap.

No description.

No description.

No description.

No description.

Evaluate interpretability methods on localizing and disentangling concepts in LLMs.

Stanford NLP Python library for benchmarking the utility of LLM interpretability methods

Stanford NLP Python library for Representation Finetuning (ReFT)

No description.

Official codebase for our paper "Do Language Models Use Their Depth Efficiently?"

A toolkit for describing model features and intervening on those features to steer behavior.

Training Sparse Autoencoders on Language Models

A Library for Aligning Causal Variables with Transformers Model

Understand and test language model architectures on synthetic tasks.

No description.

No description.

Framework for creating reliable LLM-based conversational agents

No description.

No description.

clone of LLM-Adapters

Universal and Transferable Attacks on Aligned Language Models

Mamba-Chat: A chat LLM based on the state-space model architecture 🐍

No description.

Finetuning models on SNACS corpora.

Catalogue of large language models and useful information about them.

EMNLP 2020: On the Ability and Limitations of Transformers to Recognize Formal Languages

Utilities that replicate past mechanistic interpretability work on GPT-2

Visualisation from the World Lexicon of Grammaticalization.

No description.

Natural Language Processing Research in North American Linguistics Departments

No description.

No description.

No description.

Universal Dependencies online documentation

Project website for LING 251

Predicting grammatical gender of wug words with neural sequence models.

No description.

No description.

Magahi

Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.

Notes on https://arxiv.org/pdf/1809.10756.pdf and examples implemented in Pyro

The Kholosi language of Iran.

An easy to use blogging platform, with enhanced support for Jupyter Notebooks.

My blog/website, using the Jekyll theme Hyde.

No description.

Collaborative data curation for Glottolog

No description.

Tool for uploading Eastern Chatino corpus data to Wiktionary.

Xposition but scraped (in a sort of good way).

clld app serving the CoBL database

My personal pywikibot scripts for Wiktionary.

Cataloging the semantics of adpositions (prepositions, postpositions) and case markers in multiple languages.

SWW Class of 2020 College Map

A viewer for conllulex files.

Evaluation metrics to compare AMR graphs.

No description.

An ongoing repository of data on coronavirus cases and deaths in the U.S.

Smatch tool: evaluation of AMR semantic structures

Discord Bot for Competitive Programming

No description.

Pangram solver.

Data and R code for a friction experiment in 9th grade Physics class.

Plans for a trebuchet in 9th grade Physics class that never came to fruition.

A simple list webapp. Not really that useful, but it was my first real programming project so it's here.

RobotC code for Lego Mindstorms, from STEM Locomotion class at Wyoming Seminary.

Notes for preparation for the North American Computational Linguistics Olympiad.

old Emacs config files (now I use VSCode)

No description.

An overhaul, entirely independent rewrite of FrogCraft, an IC2 Addon with theme of chemical industry.

Web development at https://www.freecodecamp.com/.

:mortar_board: Path to a free self-taught education in Computer Science!

No description.

Project Euler!!

A complete daily plan for studying to become a Google software engineer.

Family Tree Data Expression Engine

I'm learning XML and XSLT.

HTML programming practice.

2048!!