An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of…

The Hugging Face course on Transformers

Papers about training data quality management for ML models.

`dattri` is a PyTorch library for developing, benchmarking, and deploying efficient data attribution algorithms.

李宏毅2021/2022/2023春季机器学习课程课件及作业

code for ACL2024 main paper "Integrate the Essence and Eliminate the Dross: Fine-Grained Self-Consistency for Free-Form Language Generation"

[EMNLP 2024] DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models

A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.

LLM hallucination paper list

Official Implementation for the paper "Integrative Decoding: Improving Factuality via Implicit Self-consistency"

Awesome LLM Self-Consistency: a curated list of Self-consistency in Large Language Models

A curated list of LLM Interpretability related material - Tutorial, Library, Survey, Paper, Blog, etc..

TruthfulQA: Measuring How Models Imitate Human Falsehoods

Reading list of hallucination in LLMs. Check out our new survey paper: "Siren’s Song in the AI Ocean: A Survey on Hallucination in Large Language Models"

This repository provides the data and the codes used in the AAAI'24 paper, COOPER: Coordinating Specialized Agents towards a Complex Dialogue Goal.

Transformer-based Conditional Variational Autoencoder for Controllable Story Generation

[EMNLP 2024 Findings] ICON: Improving Inter-Report Consistency in Radiology Report Generation via Lesion-aware Mixup Augmentation

TACTICS (The ACademic TeachIng Purpose Car Simulator)

Config files for my GitHub profile.

Implementation of RL algorithms

Some plugins for highD series dataset

An MBTI Exploration of Large Language Models

This is the repository of EMNLP'2022 paper: "Improving Multi-turn Emotional Support Dialogue Generation with Lookahead Strategy Planning".

Codes for our paper "Enhancing Continual Relation Extraction via Classifier Decomposition" (Findings of ACL2023)

Codes for our paper "Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation" (EMNLP 2023 Findings)

Codes and datasets for our paper "ImageNetVC: Zero- and Few-Shot Visual Commonsense Evaluation on 1000 ImageNet Categories" (EMNLP 2023 Findings).