Ubiquitous Knowledge Processing Lab

All

262 repositories

llm-roleplay
Public
LLM Roleplay: Simulating Human-Chatbot Interaction
python natural-language-processing dataset-generation dialogue-systems conversational-ai chatbot-development human-ai-interaction
Python
•
Apache License 2.0
•2•39•2•0•Updated Aug 22, 2025Aug 22, 2025
PeerQA
Public
Code and Data for PeerQA: A Scientific Question Answering Dataset from Peer Reviews, NAACL 2025
nlp information-retrieval retrieval dataset question-answering peer-review rag llm
Python
•
Apache License 2.0
•2•6•0•1•Updated Aug 20, 2025Aug 20, 2025
acl2025-con-instruction
Public
Code for the 2025 ACL publication "ConInstruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities"
Python
•
Apache License 2.0
•0•5•1•3•Updated Aug 18, 2025Aug 18, 2025
arxiv2025-culturecare
Public
Repository for "Tailored Emotional LLM-Supporter: Enhancing Cultural Sensitivity" (https://arxiv.org/abs/2508.07902)
mental-health cultural emotional-support large-language-models llm
JavaScript
•
Apache License 2.0
•0•0•0•3•Updated Aug 18, 2025Aug 18, 2025
arxiv2025-assessing-paper-novelty
Public
Beyond "Not Novel Enough": Enriching Scholarly Critique with LLM-Assisted Feedback
Mermaid
•
Apache License 2.0
•0•0•0•3•Updated Aug 16, 2025Aug 16, 2025
5pils
Public
Code associated with the EMNLP 2024 Main paper: "Image, tell me your story!" Predicting the original meta-context of visual misinformation.
fake-news reverse-image-search multimodality fact-checking misinformation large-language-models multimodal-large-language-models
Python
•
Apache License 2.0
•4•42•0•0•Updated Aug 13, 2025Aug 13, 2025
naacl2025-cove
Public
Code associated with the NAACL 2025 paper "COVE: COntext and VEracity prediction for out-of-context images"
fake-news reverse-image-search fact-checking misinformation large-language-models multimodal-large-language-models misinformation-detection
Python
•
Apache License 2.0
•0•2•0•2•Updated Aug 13, 2025Aug 13, 2025
gumbel-softmax-layer-skipping-2024
Public
Code from the collaboration work between Intel and UKP. Implements a dynamic layer skipping based on Gumbel Softmax (for llama models).
Python
•
Apache License 2.0
•0•0•0•2•Updated Aug 12, 2025Aug 12, 2025
arxiv2025-expert-eval-rw
Public
The repository for "Expert Preference-based Evaluation of Automated Related Work Generation"
JavaScript
•
Apache License 2.0
•0•0•0•3•Updated Aug 12, 2025Aug 12, 2025
acl2025-stricta
Public
Repository for STRICTA: Structured Reasoning in Critical Text Assessment for Peer Review and Beyond
Python
•
Apache License 2.0
•0•1•1•3•Updated Aug 12, 2025Aug 12, 2025
arxiv2025-spare-prm
Public
Codebase for SPARE-PRM paper
Python
•
Apache License 2.0
•0•1•0•3•Updated Aug 11, 2025Aug 11, 2025
iclr2025-obscura-coder
Public
Data creation, training and eval scripts for the ObscuraCoder paper
Python
•
Apache License 2.0
•0•3•1•2•Updated Aug 11, 2025Aug 11, 2025
arxiv2025-MAGneT
Public
Repository for the paper MASCS-Gen: Multi-Agent Synthetic Counseling Session Generation
Python
•
Apache License 2.0
•0•0•0•3•Updated Aug 11, 2025Aug 11, 2025
arxiv2025-meta-review-as-dialog
Public
The repository contains the codes for our paper "Decision-Making with Deliberation: Meta-reviewing as a Document-grounded Dialogue"
Python
•
Apache License 2.0
•0•2•1•0•Updated Aug 10, 2025Aug 10, 2025
acl2025-lazy-review
Public
This repository contains the code for the ACL 2025 paper "LazyReview: A Dataset for Uncovering Lazy Thinking in NLP Peer Reviews". Project webpage available at: https://ukplab.github.io/acl2025-lazy-review/
Python
•
Apache License 2.0
•0•7•1•0•Updated Aug 10, 2025Aug 10, 2025
sentence-transformers
Public
State-of-the-Art Text Embeddings
Python
•
Apache License 2.0
•2.7k•17k•1.3k•47•Updated Aug 6, 2025Aug 6, 2025
acl25-nlp-contributions
Public
This repository contains code and data for our paper.
JavaScript
•
Apache License 2.0
•0•3•0•2•Updated Jul 23, 2025Jul 23, 2025
acl2025-modular-sentence-encoders
Public
Code for the paper "Modular Sentence Encoders: Separating Language Specialization from Cross-Lingual Alignment"
JavaScript
•
Apache License 2.0
•0•6•0•0•Updated Jul 23, 2025Jul 23, 2025
acl2025-rupta
Public
This is the official code for the paper: Robust Utility-Preserving Text Anonymization Based on Large Language Models
Python
•
Apache License 2.0
•1•4•1•1•Updated Jul 7, 2025Jul 7, 2025
arxiv2025-clca
Public
Cultural Learning-Based Culture Adaptation of Language Models (https://aclanthology.org/2025.acl-long.156/)
role-playing social-interactions synthetic-data llms cultural-adaptation cultural-learning-inspired
JavaScript
•
Apache License 2.0
•0•1•0•0•Updated Jul 6, 2025Jul 6, 2025
naacl2025-missciplus
Public
Grounding fallacious arguments in real-world evidence
Python
•
Apache License 2.0
•0•4•0•2•Updated Jul 3, 2025Jul 3, 2025
tacl2025-ood-eval-self-rationalization
Public
Code for the TACL paper "Self-Rationalization in the Wild: A Large Scale Out-of-Distribution Evaluation on NLI-related tasks"
natural-language-inference natural-language-explanations
Python
•
Apache License 2.0
•0•0•0•0•Updated Jun 26, 2025Jun 26, 2025
acl2025-diverse-cot
Public
Code for the 2025 ACL publication "Fine-Tuning on Diverse Reasoning Chains Drives Within-Inference CoT Refinement in LLMs"
cot lrm chain-of-thought large-reasoning-models reasoning-models
Python
•
Apache License 2.0
•3•31•1•0•Updated Jun 25, 2025Jun 25, 2025
clpsych2025-questmf
Public
Repository for paper "Enhancing Depression Detection via Question-wise Modality Fusion"
Python
•
Apache License 2.0
•0•4•0•0•Updated Jun 18, 2025Jun 18, 2025
qnlpai2025-ham-classifier
Public
A quantum-native efficient classification algorithm
nlp machine-learning qml cv quantum-computing classification
Python
•
Apache License 2.0
•2•7•0•3•Updated Jun 16, 2025Jun 16, 2025
naacl2025-token-weighting
Public
This is the repository for the paper "Token Weighting for Long-Range Language Modeling" to appear in NAACL 2025 (Findings)
Python
•
Apache License 2.0
•0•5•0•0•Updated Jun 13, 2025Jun 13, 2025
arxiv2025-misleading-visualizations
Public
Code and datasets accompanying the arXiv preprint: "Protecting multimodal large language models against misleading visualizations"
data-visualization question-answering misinformation large-language-models multimodal-large-language-models chart-question-answering
JavaScript
•
Apache License 2.0
•0•2•0•2•Updated Jun 13, 2025Jun 13, 2025
acl2024-sparc-and-sparp
Public
SpaRC and SpaRP: Spatial Reasoning Characterization and Path Generation for Understanding Spatial Reasoning Capability of Large Language Models
Python
•
Apache License 2.0
•1•2•0•0•Updated Jun 5, 2025Jun 5, 2025
arxiv2024-constrained-ctest-generation
Public
Code to the paper "Constrained C-Test Generation via Mixed-Integer Programming"
Python
•
Apache License 2.0
•0•0•0•0•Updated Jun 4, 2025Jun 4, 2025
ukp-project-template
Public template
The official template for new Python projects at UKP Lab
python nlp template machine-learning project-template github-actions llm
JavaScript
•
Apache License 2.0
•176•9•0•0•Updated Jun 4, 2025Jun 4, 2025