Nealcly

Selective_Context

Compress your input to ChatGPT or other LLMs, to let them process 2x more content and save 40% memory and GPU time.

GSM-IC

Grade-School Math with Irrelevant Context (GSM-IC) benchmark is an arithmetic reasoning dataset built upon GSM8K, by adding irrelevant sentences in problem descriptions. GSM-IC is constructed to evaluate the distractibility of language models.

detect-pretrain-code

This repository provides an original implementation of Detecting Pretraining Data from Large Language Models by *Weijia Shi, *Anirudh Ajith, Mengzhou Xia, Yangsibo Huang, Daogao Liu , Terra Blevins , Danqi Chen , Luke Zettlemoyer.

RemeMo

[EMNLP 2023] Once Upon a *Time* in *Graph*: Relative-Time Pretraining for Complex Temporal Reasoning

HalluQA

Dataset and evaluation script for "Evaluating Hallucinations in Chinese Large Language Models"

gecdi

The repo of "Improving Seq2Seq Grammatical Error Correction via Decoding Interventions"

AutoDAN

The official implementation of our ICLR2024 paper "AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models".

Knowledge-Constrained-Decoding

Official Code for EMNLP2023 Main Conference paper: "KCTS: Knowledge-Constrained Tree Search Decoding with Token-Level Hallucination Detection"

ctc-copy

[EMNLP'23] Code for "Non-autoregressive Text Editing with Copy-aware Latent Alignments".

BCR

Measuring and Reducing Model Update Regression in Structured Prediction for NLP

EDeR

A Dataset for Event Dependency Relation Extraction

AnnoCons

The web-based platform to visualize and annotate constituency tree.

RobustGEC

Code & Data for our Paper "RobustGEC: Robust Grammatical Error Correction Against Subtle Context Perturbation" (EMNLP 2023)

Instruction-Tuning-Papers

Reading list of Instruction-tuning. A trend starts from Natrural-Instruction (ACL 2022), FLAN (ICLR 2022) and T0 (ICLR 2022).

belebele

Repo for the Belebele dataset, a massively multilingual reading comprehension dataset.

self-speculative-decoding

Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**

Xwin-LM

Xwin-LM: Powerful, Stable, and Reproducible LLM Alignment

EKD_Impacts_PKG

This is the respository for paper "Merge Conflicts! Exploring the Impacts of External Distractors to Parametric Knowledge Graphs"

DoLa

Official implementation for the paper "DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models"

Baichuan2

A series of large language models developed by Baichuan Intelligent Technology

LLMSpeculativeSampling

Fast inference from large lauguage models via speculative decoding

Post-Instruction

LLM-Ref

chatgpt-prompts-for-academic-writing

This list of writing prompts covers a range of topics and tasks, including brainstorming research ideas, improving language and style, conducting literature reviews, and developing research plans.

synjax

gpt_academic

为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, moss等。

tdc2023-starter-kit

This is the starter kit for the Trojan Detection Challenge 2023 (LLM Edition), a NeurIPS 2023 competition.

tdc-starter-kit

Starter kit and data loading code for the Trojan Detection Challenge NeurIPS 2022 competition

alpaca_farm

A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.

direct-preference-optimization

Reference implementation for DPO (Direct Preference Optimization)