29 citations · 48 across the 24 of their papers we have counts for
27 papers
Parameter Exploration for RLVR via Variational Learning
Vatsal Venkatkrishna, Nico Daheim, Iryna Gurevych
Exploration has been a focus of reinforcement learning research for a long time. Recently, there has been growing evidence that it is also an important ingredient in LLM reinforcem…
'Your AI Text is not Mine': Redefining and Evaluating AI-generated Text Detection under Realistic Assumptions
Nils Dycke, Marina Sakharova, Nico Daheim +1
Although it is generally agreed that AI-generated text poses a broad societal risk, there is no common understanding in the AI-generated text detection literature on what constitut…
SVRG and Beyond via Posterior Correction
Nico Daheim, Thomas Möllenhoff, Ming Liang Ang +1
Stochastic Variance Reduced Gradient (SVRG) and its variants aim to speed-up training by using gradient corrections. Originally proposed over a decade ago, these methods have never…
Improving LoRA with Variational Learning
Bai Cong, Nico Daheim, Yuesong Shen +3
Bayesian methods have recently been used to improve LoRA finetuning and, although they improve calibration, their effect on other metrics (such as accuracy) is marginal and can som…
A Head to Predict and a Head to Question: Pre-trained Uncertainty Quantification Heads for Hallucination Detection in LLM Outputs
Artem Shelmanov, Ekaterina Fadeeva, Akim Tsvigun +9
Large Language Models (LLMs) have the tendency to hallucinate, i.e., to sporadically generate false or fabricated information. This presents a major challenge, as hallucinations of…
From Problem-Solving to Teaching Problem-Solving: Aligning LLMs with Pedagogy using Reinforcement Learning
David Dinucu-Jianu, Jakub Macina, Nico Daheim +3
Large language models (LLMs) can transform education, but their optimization for direct question-answering often undermines effective pedagogy which requires strategically withhold…
Token Weighting for Long-Range Language Modeling
Falko Helm, Nico Daheim, Iryna Gurevych
Many applications of large language models (LLMs) require long-context understanding, but models continue to struggle with such tasks. We hypothesize that conventional next-token p…
Uncertainty-Aware Decoding with Minimum Bayes Risk
Nico Daheim, Clara Meister, Thomas Möllenhoff +1
Despite their outstanding performance in the majority of scenarios, contemporary language models still occasionally generate undesirable outputs, for example, hallucinated text. Wh…
MathTutorBench: A Benchmark for Measuring Open-ended Pedagogical Capabilities of LLM Tutors
Jakub Macina, Nico Daheim, Ido Hakimi +3
Evaluating the pedagogical capabilities of AI-based tutoring models is critical for making guided progress in the field. Yet, we lack a reliable, easy-to-use, and simple-to-run eva…
Variational Model Merging for Pareto Front Estimation in Multitask Finetuning
Hugo Monzón Maldonado, Nico Daheim, Thomas Möllenhoff +2
Pareto fronts are useful to find good task-mixing strategies for multitask finetuning, but they are also costly to compute. To reduce costs, recent works have used existing model m…
Variational Low-Rank Adaptation Using IVON
Bai Cong, Nico Daheim, Yuesong Shen +4
We show that variational learning can significantly improve the accuracy and calibration of Low-Rank Adaptation (LoRA) without a substantial increase in the cost. We replace AdamW…
Stepwise Verification and Remediation of Student Reasoning Errors with Large Language Model Tutors
Nico Daheim, Jakub Macina, Manu Kapur +2
Large language models (LLMs) present an opportunity to scale high-quality personalized education to all. A promising approach towards this means is to build dialog tutoring models…
Book2Dial: Generating Teacher-Student Interactions from Textbooks for Cost-Effective Development of Educational Chatbots
Junling Wang, Jakub Macina, Nico Daheim +2
Educational chatbots are a promising tool for assisting student learning. However, the development of effective chatbots in education has been challenging, as high-quality data is…
Socratic Reasoning Improves Positive Text Rewriting
Anmol Goel, Nico Daheim, Christian Montag +1
Reframing a negative into a positive thought is at the crux of several cognitive approaches to mental health and psychotherapy that could be made more accessible by large language…
Variational Learning is Effective for Large Deep Networks
Yuesong Shen, Nico Daheim, Bai Cong +8
We give extensive empirical evidence against the common belief that variational learning is ineffective for large neural networks. We show that an optimizer called Improved Variati…
Model Merging by Uncertainty-Based Gradient Matching
Nico Daheim, Thomas Möllenhoff, Edoardo Maria Ponti +2
Models trained on different datasets can be merged by a weighted-averaging of their parameters, but why does it work and when can it fail? Here, we connect the inaccuracy of weight…
Uncertainty in Natural Language Generation: From Theory to Applications
Joris Baan, Nico Daheim, Evgenia Ilia +7
Recent advances of powerful Language Models have allowed Natural Language Generation (NLG) to emerge as an important technology that can not only perform traditional tasks like sum…
MathDial: A Dialogue Tutoring Dataset with Rich Pedagogical Properties Grounded in Math Reasoning Problems
Jakub Macina, Nico Daheim, Sankalan Pal Chowdhury +4
While automatic dialogue tutors hold great potential in making education personalized and more accessible, research on such systems has been hampered by a lack of sufficiently larg…
Task-oriented Document-Grounded Dialog Systems by HLTPR@RWTH for DSTC9 and DSTC10
David Thulke, Nico Daheim, Christian Dugast +1
This paper summarizes our contributions to the document-grounded dialog tasks at the 9th and 10th Dialog System Technology Challenges (DSTC9 and DSTC10). In both iterations the tas…
Elastic Weight Removal for Faithful and Abstractive Dialogue Generation
Nico Daheim, Nouha Dziri, Mrinmaya Sachan +2
Ideally, dialogue systems should generate responses that are faithful to the knowledge contained in relevant documents. However, many models generate hallucinated responses instead…
Opportunities and Challenges in Neural Dialog Tutoring
Jakub Macina, Nico Daheim, Lingzhi Wang +4
Designing dialog tutors has been challenging as it involves modeling the diverse and complex pedagogical strategies employed by human tutors. Although there have been significant r…
Poor Man's Quality Estimation: Predicting Reference-Based MT Metrics Without the Reference
Vilém Zouhar, Shehzaad Dhuliawala, Wangchunshu Zhou +4
Machine translation quality estimation (QE) predicts human judgements of a translation hypothesis without seeing the reference. State-of-the-art QE systems based on pretrained lang…
Controllable Factuality in Document-Grounded Dialog Systems Using a Noisy Channel Model
Nico Daheim, David Thulke, Christian Dugast +1
In this work, we present a model for document-grounded response generation in dialog that is decomposed into two components according to Bayes theorem. One component is a tradition…
GEMv2: Multilingual NLG Benchmarking in a Single Line of Code
Sebastian Gehrmann, Abhik Bhattacharjee, Abinaya Mahendiran +74
Evaluation in machine learning is usually informed by past choices, for example which datasets or metrics to use. This standardization enables the comparison on equal footing using…