Ubiquitous Knowledge Processing Lab

sentence-transformers

Multilingual Sentence & Image Embeddings with BERT

on-emergence

Codes and files for the paper Are Emergent Abilities in Large Language Models just In-Context Learning

lagonn

Source code and data for Like a Good Nearest Neighbor

arxiv2018-bayesian-ensembles

arxiv2023-dapr

AdaSent

This repository contains the code for the EMNLP'23 paper "AdaSent: Efficient Domain-Adapted Sentence Embeddings for Few-Shot Classification"

acl2020-empowering-active-learning

arxiv2024-triple-encoders

triple-encoders is a library for contextualizing distributed Sentence Transformers representations.

arxiv2024-conditional-reasoning-llms

Code Prompting Elicits Conditional Reasoning Abilities in Text+Code LLMs. arXiv 2024

ukp-project-template

The official template for new Python projects at UKP Lab

a-template-is-all-you-meme

Source code and data

arxiv2024-ircoder

Data creation, training and eval scripts for the IRCoder paper

maps

Multicultural Proverbs and Sayings

aacl2022-TexPrax

cl2022-annotation-curriculum

Source code and user models from our experiments of our CL 2022 submission

in-context-pvi

Codes and files for the paper Measuring Pointwise V-Usable Information In-Context-ly

arxiv2023-sociodemographic-prompting

README

CARE_broker

Project CARE - NLP Broker

eacl2024-cross-topic-probing

This repository includes the code to probe language models for the gap between In- and Cross-Topic generalization.

eacl2024-doc-structure

This is the repository for the EACL 2024 paper "Document Structure in Long Document Transformers".

emnlp2023-learning-from-free-text-human-feedback

Code and data for the EMNLP 2023 paper "Learning From Free-Text Human Feedback -- Collect New Datasets or Extend Existing Ones".

acl2019-ctest-difficulty-manipulation

FEDI

This is the repository for the paper "Learning from Emotions, Demographic Information and Implicit User Feedback in Task-Oriented Document-Grounded Dialogues", which is currently available in arxiv.

naacl2024-prompt-sensitivity

Codes and files for the paper How are Prompts Different in Terms of Sensitivity

acl2024-missci

Dataset and code for our paper about reconstructing misrepresented science.

arxiv2024-constrained-ctest-generation

Code to the paper "Constrained C-Test Generation via Mixed-Integer Programming"

iclr2024-model-merging

This is the repository for "Model Merging by Uncertainty-Based Gradient Matching", ICLR 2024.

naacl2024-ewr

Code for "Elastic Weight Removal for Faithful and Abstractive Dialogue Generation", NAACL 2024

naacl2024-fun

Fisher information based schedule unfreezing

qanno

Code for our paper "Analyzing Dataset Annotation Quality Management in the Wild"