Papers by Katrin Tomanek

5 papers
Detecting Hallucination and Coverage Errors in Retrieval Augmented Generation for Controversial Topics (2024.lrec-main)

Copied to clipboard

Challenge: a growing audience of users is engaging with LLM-driven chatbots.
Approach: They propose a strategy to handle controversial topics in LLM-based chatbots based on Wikipedia’s Neutral Point of View principle.
Outcome: The proposed methods detect errors in the tuned LLM responses even when no training data is available.
Towards Agile Text Classifiers for Everyone (2023.findings-emnlp)

Copied to clipboard

Challenge: Text-based safety classifiers are widely used for content moderation and increasingly to tune generative language model behavior.
Approach: They propose to use small, targeted datasets to train safety classifiers using small, iterative datasets that can be quickly developed for a particular policy.
Outcome: The proposed method can be quickly developed for a specific policy with a labeled dataset of as few as 80 examples.
Residual Adapters for Parameter-Efficient ASR Adaptation to Atypical and Accented Speech (2021.emnlp-main)

Copied to clipboard

Challenge: Automatic Speech Recognition systems perform poorly on atypical speech and heavily accented speech.
Approach: They add a residual adapter to the encoder layer to improve model adaptation . they show that the residual adapters update only a tiny fraction of the model parameters .
Outcome: The proposed model fine-tuning improves performance on atypical and accented speech . the system can update only a tiny fraction of the model parameters .
Context-Aware Abbreviation Expansion Using Large Language Models (2022.naacl-main)

Copied to clipboard

Challenge: Existing paradigms for text entry in augmentative and alternative communication (AAC) for people with severe motor impairments require 3-5 predictions to save keystrokes.
Approach: They propose a paradigm in which phrases are abbreviated aggressively as word-initial letters.
Outcome: The proposed paradigm can save up to 77% on expansions on conversation turn . the proposed paradigm could be used in augmentative and alternative communication (AAC)
Reassessing Active Learning Adoption in Contemporary NLP: A Community Survey (2026.eacl-long)

Copied to clipboard

Challenge: a longstanding strategy to reduce annotation costs is active learning . data annotation is expected to remain important and active learning to stay relevant .
Approach: They conduct an online survey to assess the perceived relevance of data annotation and active learning . they propose a strategy to reduce annotation costs using active learning, an iterative process .
Outcome: The proposed strategies reduce setup complexity and uncertainty cost while maintaining model performance.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations