UKPLab
Built from UKPLab's public GitHub profile, Darmstadt, Germany. Not on Take My Repo yet, so there are no posts or updates here.
Code associated with the EMNLP 2024 Main paper: "Image, tell me your story!" Predicting the original meta-context of visual misinformation.
Code associated with NLPeer: A unified resource for the study of peer review
Code for the 2025 ACL publication "Fine-Tuning on Diverse Reasoning Chains Drives Within-Inference CoT Refinement in LLMs"
Codes and files for the paper Are Emergent Abilities in Large Language Models just In-Context Learning
Code and Data for PeerQA: A Scientific Question Answering Dataset from Peer Reviews, NAACL 2025 https://aclanthology.org/2025.naacl-long.22/
Argotario: a multi-lingual serious game to tackle fallacious argumentation
A curated collection of papers, datasets, and resources on the topic of misleading chart understanding
This is the official code for the paper: Robust Utility-Preserving Text Anonymization Based on Large Language Models
Code for Incorporating Relevance Feedback for Information-Seeking Retrieval using Few-Shot Document Re-Ranking, EMNLP 2022, https://aclanthology.org/2022.emnlp-main.614
Code for the 2025 ACL publication "ConInstruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities"
Code repository for the paper "The Inherent Limits of Pretrained LLMs: The Unexpected Convergence of Instruction Tuning and In-Context Learning Capabilities"
[EACL Main] GRITHopper: Decomposition-Free Multi-Hop Dense Retrieval
Plug-and-play implementation of Supervised Multi-Dimensional Scaling from the paper "Shape Happens: Automatic Feature Manifold Discovery in LLMs via Supervised Multi-Dimensional Scaling."
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/
In-depth research impact summarization through fine-grained temporal citation analysis
Beyond "Not Novel Enough": Enriching Scholarly Critique with LLM-Assisted Feedback