8 papers
Towards Automated Error Discovery: A Study in Conversational AI
Dominic Petrak, Thy Thy Tran, Iryna Gurevych
Although LLM-based conversational agents demonstrate strong fluency and coherence, they still produce undesirable behaviors (errors) that are challenging to prevent from reaching u…
Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities
Jiahui Geng, Thy Thy Tran, Preslav Nakov +1
Existing attacks against multimodal language models (MLLMs) primarily communicate instructions through text accompanied by adversarial images. In contrast, we exploit the capabilit…
Efficient Performance Tracking: Leveraging Large Language Models for Automated Construction of Scientific Leaderboards
Furkan Şahinuç, Thy Thy Tran, Yulia Grishina +3
Scientific leaderboards are standardized ranking systems that facilitate evaluating and comparing competitive methods. Typically, a leaderboard is defined by a task, dataset, and e…
A Course Shared Task on Evaluating LLM Output for Clinical Questions
Yufang Hou, Thy Thy Tran, Doan Nam Long Vu +4
This paper presents a shared task that we organized at the Foundations of Language Technology (FoLT) course in 2023/2024 at the Technical University of Darmstadt, which focuses on…
Learning from Implicit User Feedback, Emotions and Demographic Information in Task-Oriented and Document-Grounded Dialogues
Dominic Petrak, Thy Thy Tran, Iryna Gurevych
Implicit user feedback, user emotions and demographic information have shown to be promising sources for improving the accuracy and user engagement of responses generated by dialog…
Dior-CVAE: Pre-trained Language Models and Diffusion Priors for Variational Dialog Generation
Tianyu Yang, Thy Thy Tran, Iryna Gurevych
Current variational dialog models have employed pre-trained language models (PLMs) to parameterize the likelihood and posterior distributions. However, the Gaussian assumption made…
The Devil is in the Details: On Models and Training Regimes for Few-Shot Intent Classification
Mohsen Mesgar, Thy Thy Tran, Goran Glavas +1
Few-shot Intent Classification (FSIC) is one of the key challenges in modular task-oriented dialog systems. While advanced FSIC methods are similar in using pretrained language mod…
Revisiting Unsupervised Relation Extraction
Thy Thy Tran, Phong Le, Sophia Ananiadou
Unsupervised relation extraction (URE) extracts relations between named entities from raw text without manually-labelled data and existing knowledge bases (KBs). URE methods can be…