AIConfPaper
← Search

Stefan Winkler

8 accepted papers

2025

MEDSAGE: Enhancing Robustness of Medical Dialogue Summarization to ASR Errors with LLM-generated Synthetic Dialogues

Kuluhan Binici, Abhinav Ramesh Kashyap, Viktor Schlegel, Andy T. Liu, Vijay Prakash Dwivedi, Thanh-Tung Nguyen +3
AAAI 2025technical

Automatic Speech Recognition (ASR) systems are pivotal in transcribing speech into text, yet the errors they introduce can significantly degrade the performance of downstream tasks like summarization. This issue is particularly pronounced in clinical dialogue summarization, a low-resource domain whe…

Cited by 0Source ↗PDF ↗Scholar ↗
2024

M-QALM: A Benchmark to Assess Clinical Reading Comprehension and Knowledge Recall in Large Language Models via Question Answering

Anand Subramanian, Viktor Schlegel, Abhinav Ramesh Kashyap, Thanh-Tung Nguyen, Vijay Prakash Dwivedi, Stefan Winkler
ACL 2024findings

There is vivid research on adapting Large Language Models (LLMs) to perform a variety of tasks in high-stakes domains such as healthcare. Despite their popularity, there is a lack of understanding of the extent and contributing factors that allow LLMs to recall relevant knowledge and combine it with…

Cited by 2Source ↗PDF ↗code ↗Scholar ↗
2024

MaxEnt Loss: Constrained Maximum Entropy for Calibration under Out-of-Distribution Shift

Dexter Neo, Stefan Winkler, Tsuhan Chen
AAAI 2024technical

We present a new loss function that addresses the out-of-distribution (OOD) network calibration problem. While many objective functions have been proposed to effectively calibrate models in-distribution, our findings show that they do not always fare well OOD. Based on the Principle of Maximum Entro…

Cited by 4Source ↗PDF ↗code ↗Scholar ↗
2024

Seemingly Plausible Distractors in Multi-Hop Reasoning: Are Large Language Models Attentive Readers?

Neeladri Bhuiya, Viktor Schlegel, Stefan Winkler
EMNLP 2024main

State-of-the-art Large Language Models (LLMs) are accredited with an increasing number of different capabilities, ranging from reading comprehension over advanced mathematical and reasoning skills to possessing scientific knowledge. In this paper we focus on multi-hop reasoning—the ability to identi…

Cited by 3Source ↗PDF ↗code ↗Scholar ↗
2023

A Two-Stage Decoder for Efficient ICD Coding

Thanh-Tung Nguyen, Viktor Schlegel, Abhinav Ramesh Kashyap, Stefan Winkler
ACL 2023findings

Clinical notes in healthcare facilities are tagged with the International Classification of Diseases (ICD) code; a list of classification codes for medical diagnoses and procedures. ICD coding is a challenging multilabel text classification problem due to noisy clinical document inputs and long-tail…

Cited by 10Source ↗PDF ↗code ↗Scholar ↗
2019

The Unusual Effectiveness of Averaging in GAN Training

Yasin Yaz{\i}c{\i}, Chuan-Sheng Foo, Stefan Winkler, Kim-Hui Yap, Georgios Piliouras, Vijay Chandrasekhar
ICLR 2019poster

We examine two different techniques for parameter averaging in GAN training. Moving Average (MA) computes the time-average of parameters, whereas Exponential Moving Average (EMA) computes an exponentially discounted sum. Whilst MA is known to lead to convergence in bilinear settings, we provide the…

Cited by 105Source ↗PDF ↗code ↗Scholar ↗
2017

Episodic CAMN: Contextual Attention-Based Memory Networks With Iterative Feedback for Scene Labeling

Abrar H. Abdulnabi, Bing Shuai, Stefan Winkler, Gang Wang
CVPR 2017poster

Scene labeling can be seen as a sequence-sequence prediction task (pixels-labels), and it is quite important to leverage relevant context to enhance the performance of pixel classification. In this paper, we introduce an episodic attention-based memory network to achieve the goal. We present a unifi…

Cited by 17PDF ↗Scholar ↗