Test-time preferenece optimization (ICML 2025).

Code & Data for our Paper "Alleviating Hallucinations of Large Language Models through Induced Hallucinations"

A series of large language models developed by Baichuan Intelligent Technology

Code for ACL 2020 paper: "Extractive Summarization as Text Matching"

🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022

This repository collects an extensive list of awesome papers about Story Generation / Storytelling, exclusively focusing on the era of Large Language Models (LLMs).

Revisiting Cross-Lingual Summarization: A Corpus-based Study and A New Benchmark with Improved Annotation

Failure archive for ChatGPT and similar models

[EMNLP 2023] Enabling Large Language Models to Generate Text with Citations. Paper: https://arxiv.org/abs/2305.14627

800,000 step-level correctness labels on LLM solutions to MATH problems

Machine-generated text detection in the wild (ACL 2024)

Topic-Aware Convolutional Neural Networks for Extreme Summarization

Reverse Instructions to generate instruction tuning data with corpus examples

AnchiBERT: A Pre-Trained Model for Ancient Chinese Language Understanding and Generation(古文预训练模型)

Instruction Tuning with GPT-4

[ACL 2023] Reasoning with Language Model Prompting: A Survey

This project is an attempt to create a common metric to test LLM's for progress in eliminating hallucinations which is the most serious current problem in widespread adoption of LLM's for many real…

An open-source tool-augmented conversational language model from Fudan University

The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language.

Calculating ROUGE score between two files (line-by-line)

Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

Benchmarking large language models' complex reasoning ability with chain-of-thought prompting

Bidirectional Logic Evaluation for Consistency (BLEC), an auto metric for logic consistency between NL and PL

Semantic Parsing for Conversational Question Answering over Large Knowledge Graphs

Features & Calculation for Summarization Dataset