Amazon Science

RAGChecker

RAGChecker: A Fine-grained Framework For Diagnosing RAG

RefChecker

RefChecker provides automatic checking pipeline and benchmark dataset for detecting fine-grained hallucinations generated by Large Language Models.

wqa_tanda

This repo provides code and data used in our TANDA paper.

alexa-arena

redset

Redset is a dataset containing three months worth of user query metadata that ran on a selected sample of instances in the Amazon Redshift fleet. We provide query metadata for 200 provisioned and serverless instances each.

azcausal

Causal Inference in Python

carbon-assessment-with-ml

CaML: Carbon Footprinting of Household Products with Zero-Shot Semantic Text Similarity

AdaSlot

Official implementation of the CVPR'24 paper [Adaptive Slot Attention: Object Discovery with Dynamic Slot Number]

relaxed-adaptive-projection

hr-multiwoz-tod-llm-agent

incremental-parsing

Incremental Python parser for constrained generation of code by LLMs.

BYOKG-NAACL24

text_generation_diffusion_llm_topic

Topic Embedding, Text Generation and Modeling using diffusion

unique-batches

llm-hallucinations-factual-qa

synthesizrr

Synthesizing realistic and diverse text-datasets from augmented LLMs

avgen-eval-toolkit

aws-dialogue-qa-pair-generation

dlwp-benchmark

Code for the paper: Comparing and Contrasting Deep Learning Weather Prediction Backbones on Navier-Stokes and Atmospheric Dynamics

iesum

sumren

network-deconvolution-pp

causal-validation

Validate your causal models!

Network-Usable-Info-Framework

DOSSIER

handling-ontology-gaps-in-semantic-parsing

Repository of the paper Handling Hallucinations In Neural Semantic Parsing.

ssepy

Python package for stratifying, sampling, and estimating model performance efficiently.

aws-intent-detect-neg-implicature-dataset

Buggy-Aware-CodeLM

disc-health-risk