Mattias Wahde
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Mattias Wahde has a total of 31 co-authors. Here are the top co-authors by number of shared publications:
Jimmy Pettersson
Department of Applied Mechanics, Chalmers University of Technology, 412 96 Göteborg, Sweden
3 shared publications- Krister Wolff
Chalmers University of Technology 412 96 Göteborg Sweden
3 shared publications - Marco Luigi Della Vedova
Chalmers University of Technology
3 shared publications - Minerva Suvanto
Chalmers University of Technology
3 shared publications David Sandberg
Department of Applied Mechanics, Chalmers University of Technology, 412 96 Göteborg, Sweden
2 shared publicationsKrister Wolff
Department of Applied Mechanics, Chalmers University of Technology, 412 96 Göteborg, Sweden
2 shared publications
Latest Publications
- Open Access
- 3 March 2026
- Published by Linkoping University Electronic Press in Northern European Journal of Language Technology
- Vol. 12 (1) , 118–123
A note on the detection of LLM-generated political speeches
We use a recent data set (ParliaBench) containing political speeches as well as LLM-generated versions of such speeches to investigate whether the latter can be detected as being LLM-generated. We find that, for this data set, a linear, interpretable classifier can easily do so, achieving an F1 score of around 0.96 - 0.98. The ability of a classifier to distinguish LLM-generated text from human-written text is significant since it has many potential uses, for example in detecting potential undisclosed use of LLM-generated text in political speeches.
- 3 March 2026
- Published by Linkoping University Electronic Press in Northern European Journal of Language Technology
- Vol. 12 (1) , 118–123
Open AccessA note on the detection of LLM-generated political speeches
We use a recent data set (ParliaBench) containing political speeches as well as LLM-generated versions of such speeches to investigate whether the latter can be detected as being LLM-generated. We find that, for this data set, a linear, interpretable classifier can easily do so, achieving an F1 score of around 0.96 - 0.98. The ability of a classifier to distinguish LLM-generated text from human-written text is significant since it has many potential uses, for example in detecting potential undisclosed use of LLM-generated text in political speeches.
- Open Access
Interpretable Text Classification Applied to the Detection of LLM-generated Creative Writing
We consider the problem of distinguishing human-written creative fiction (excerpts from novels) from similar text generated by an LLM. Our results show that, while human observers perform poorly (near chance levels) on this binary classification task, a variety of machine-learning models achieve accuracy in the range 0.93 - 0.98 over a previously unseen test set, even using only short samples and single-token (unigram) features. We therefore employ an inherently interpretable (linear) classifier (with a test accuracy of 0.98), in order to elucidate the underlying reasons for this high accuracy. In our analysis, we identify specific unigram features indicative of LLM-generated text, one of the most important being that the LLM tends to use a larger variety of synonyms, thereby skewing the probability distributions in a manner that is easy to detect for a machine learning classifier, yet very difficult for a human observer. Four additional explanation categories were also identified, namely, temporal drift, Americanisms, foreign language usage, and colloquialisms. As identification of the AI-generated text depends on a constellation of such features, the classification appears robust, and therefore not easy to circumvent by malicious actors intent on misrepresenting AI-generated text as human work.
Open AccessInterpretable Text Classification Applied to the Detection of LLM-generated Creative Writing
We consider the problem of distinguishing human-written creative fiction (excerpts from novels) from similar text generated by an LLM. Our results show that, while human observers perform poorly (near chance levels) on this binary classification task, a variety of machine-learning models achieve accuracy in the range 0.93 - 0.98 over a previously unseen test set, even using only short samples and single-token (unigram) features. We therefore employ an inherently interpretable (linear) classifier (with a test accuracy of 0.98), in order to elucidate the underlying reasons for this high accuracy. In our analysis, we identify specific unigram features indicative of LLM-generated text, one of the most important being that the LLM tends to use a larger variety of synonyms, thereby skewing the probability distributions in a manner that is easy to detect for a machine learning classifier, yet very difficult for a human observer. Four additional explanation categories were also identified, namely, temporal drift, Americanisms, foreign language usage, and colloquialisms. As identification of the AI-generated text depends on a constellation of such features, the classification appears robust, and therefore not easy to circumvent by malicious actors intent on misrepresenting AI-generated text as human work.
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 23, 2507505
Meter-Resolution Canopy Height Data Alone Can Be Used for Predicting the Conservation Value of Boreal Forests
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 23, 2507505
Open AccessMeter-Resolution Canopy Height Data Alone Can Be Used for Predicting the Conservation Value of Boreal Forests
- 26 April 2025
- Published by Springer Nature
- p. 207-221
Part-of-Speech Taggers Make Errors on Unambiguous Sentences
- 26 April 2025
- Published by Springer Nature
- p. 207-221
Part-of-Speech Taggers Make Errors on Unambiguous Sentences
- Open Access
- 4 May 2023
- Published by Springer Nature in Evolutionary Intelligence
- Vol. 17 (1) , 609-621
An interpretable method for automated classification of spoken transcripts and written text
We investigate the differences between spoken language (in the form of radio show transcripts) and written language (Wikipedia articles) in the context of text classification. We present a novel, interpretable method for text classification, involving a linear classifier using a large set of $$n-$$ gram features, and apply it to a newly generated data set with sentences originating either from spoken transcripts or written text. Our classifier reaches an accuracy less than 0.02 below that of a commonly used classifier (DistilBERT) based on deep neural networks (DNNs). Moreover, our classifier has an integrated measure of confidence, for assessing the reliability of a given classification. An online tool is provided for demonstrating our classifier, particularly its interpretable nature, which is a crucial feature in classification tasks involving high-stakes decision-making. We also study the capability of DistilBERT to carry out fill-in-the-blank tasks in either spoken or written text, and find it to perform similarly in both cases. Our main conclusion is that, with careful improvements, the performance gap between classical methods and DNN-based methods may be reduced significantly, such that the choice of classification method comes down to the need (if any) for interpretability.- 4 May 2023
- Published by Springer Nature in Evolutionary Intelligence
- Vol. 17 (1) , 609-621
Open AccessAn interpretable method for automated classification of spoken transcripts and written text
We investigate the differences between spoken language (in the form of radio show transcripts) and written language (Wikipedia articles) in the context of text classification. We present a novel, interpretable method for text classification, involving a linear classifier using a large set of $$n-$$ gram features, and apply it to a newly generated data set with sentences originating either from spoken transcripts or written text. Our classifier reaches an accuracy less than 0.02 below that of a commonly used classifier (DistilBERT) based on deep neural networks (DNNs). Moreover, our classifier has an integrated measure of confidence, for assessing the reliability of a given classification. An online tool is provided for demonstrating our classifier, particularly its interpretable nature, which is a crucial feature in classification tasks involving high-stakes decision-making. We also study the capability of DistilBERT to carry out fill-in-the-blank tasks in either spoken or written text, and find it to perform similarly in both cases. Our main conclusion is that, with careful improvements, the performance gap between classical methods and DNN-based methods may be reduced significantly, such that the choice of classification method comes down to the need (if any) for interpretability. - Open Access
- 10 June 2022
- Published by Taylor & Francis in International Journal of Human–Computer Interaction
- Vol. 39 (9) , 1856-1873
DAISY: An Implementation of Five Core Principles for Transparent and Accountable Conversational AI
We present a detailed implementation of five core principles for transparent and acccountable conversational AI, namely interpretability, inherent capability to explain, independent data, interactive learning, and inquisitiveness. This implementation is a dialogue manager called DAISY that serves as the core part of a conversational agent. We show how DAISY-based agents are trained with human-machine interaction, a process that also involves suggestions for generalization from the agent itself. Moreover, these agents are capable to provide a concise and clear explanation of the actions required to reach a conclusion. Deep neural networks (DNNs) are currently the de facto standard in conversational AI. We therefore formulate a comparison between DAISY-based agents and two methods that use DNNs, on two popular data sets involving multi-domain task-oriented dialogue. Specifically, we provide quantitative results related to entity retrieval and qualitative results in terms of the type of errors that may occur. The results show that DAISY-based agents achieve superior precision at the price of lower recall, an outcome that might be preferable in task-oriented settings. Ultimately, and especially in view of their high degree of interpretability, DAISY-based agents are a fundamentally different alternative to the currently popular DNN-based methods.
- 10 June 2022
- Published by Taylor & Francis in International Journal of Human–Computer Interaction
- Vol. 39 (9) , 1856-1873
Open AccessDAISY: An Implementation of Five Core Principles for Transparent and Accountable Conversational AI
We present a detailed implementation of five core principles for transparent and acccountable conversational AI, namely interpretability, inherent capability to explain, independent data, interactive learning, and inquisitiveness. This implementation is a dialogue manager called DAISY that serves as the core part of a conversational agent. We show how DAISY-based agents are trained with human-machine interaction, a process that also involves suggestions for generalization from the agent itself. Moreover, these agents are capable to provide a concise and clear explanation of the actions required to reach a conclusion. Deep neural networks (DNNs) are currently the de facto standard in conversational AI. We therefore formulate a comparison between DAISY-based agents and two methods that use DNNs, on two popular data sets involving multi-domain task-oriented dialogue. Specifically, we provide quantitative results related to entity retrieval and qualitative results in terms of the type of errors that may occur. The results show that DAISY-based agents achieve superior precision at the price of lower recall, an outcome that might be preferable in task-oriented settings. Ultimately, and especially in view of their high degree of interpretability, DAISY-based agents are a fundamentally different alternative to the currently popular DNN-based methods.
- Open Access
- 20 November 2021
- Published by Association for Computing Machinery (ACM)
- p. 50-54
The five Is: Key principles for interpretable and safe conversational AI
In this position paper, we present five key principles, namely interpretability, inherent capability to explain, independent data, interactive learning, and inquisitiveness, for the development of conversational AI that, unlike the currently popular black box approaches, is transparent and accountable. At present, there is a growing concern with the use of black box statistical language models: While displaying impressive average performance, such systems are also prone to occasional spectacular failures, for which there is no clear remedy. In an effort to initiate a discussion on possible alternatives, we outline and exemplify how our five principles enable the development of conversational AI systems that are transparent and thus safer for use. We also present some of the challenges inherent in the implementation of those principles.
- 20 November 2021
- Published by Association for Computing Machinery (ACM)
- p. 50-54
Open AccessThe five Is: Key principles for interpretable and safe conversational AI
In this position paper, we present five key principles, namely interpretability, inherent capability to explain, independent data, interactive learning, and inquisitiveness, for the development of conversational AI that, unlike the currently popular black box approaches, is transparent and accountable. At present, there is a growing concern with the use of black box statistical language models: While displaying impressive average performance, such systems are also prone to occasional spectacular failures, for which there is no clear remedy. In an effort to initiate a discussion on possible alternatives, we outline and exemplify how our five principles enable the development of conversational AI systems that are transparent and thus safer for use. We also present some of the challenges inherent in the implementation of those principles.
- Open Access
Lidar–Camera Semi-Supervised Learning for Semantic Segmentation
In this work, we investigated two issues: (1) How the fusion of lidar and camera data can improve semantic segmentation performance compared with the individual sensor modalities in a supervised learning context; and (2) How fusion can also be leveraged for semi-supervised learning in order to further improve performance and to adapt to new domains without requiring any additional labelled data. A comparative study was carried out by providing an experimental evaluation on networks trained in different setups using various scenarios from sunny days to rainy night scenes. The networks were tested for challenging, and less common, scenarios where cameras or lidars individually would not provide a reliable prediction. Our results suggest that semi-supervised learning and fusion techniques increase the overall performance of the network in challenging scenarios using less data annotations.
Open AccessLidar–Camera Semi-Supervised Learning for Semantic Segmentation
In this work, we investigated two issues: (1) How the fusion of lidar and camera data can improve semantic segmentation performance compared with the individual sensor modalities in a supervised learning context; and (2) How fusion can also be leveraged for semi-supervised learning in order to further improve performance and to adapt to new domains without requiring any additional labelled data. A comparative study was carried out by providing an experimental evaluation on networks trained in different setups using various scenarios from sunny days to rainy night scenes. The networks were tested for challenging, and less common, scenarios where cameras or lidars individually would not provide a reliable prediction. Our results suggest that semi-supervised learning and fusion techniques increase the overall performance of the network in challenging scenarios using less data annotations.
- Open Access
Model Learning with Personalized Interpretability Estimation (ML-PIE)
High-stakes applications require AI-generated models to be interpretable. Current algorithms for the synthesis of potentially interpretable models rely on objectives or regularization terms that represent interpretability only coarsely (e.g., model size) and are not designed for a specific user. Yet, interpretability is intrinsically subjective. In this paper, we propose an approach for the synthesis of models that are tailored to the user by enabling the user to steer the model synthesis process according to her or his preferences. We use a bi-objective evolutionary algorithm to synthesize models with trade-offs between accuracy and a user-specific notion of interpretability. The latter is estimated by a neural network that is trained concurrently to the evolution using the feedback of the user, which is collected using uncertainty-based active learning. To maximize usability, the user is only asked to tell, given two models at the time, which one is less complex. With experiments on two real-world datasets involving 61 participants, we find that our approach is capable of learning estimations of interpretability that can be very different for different users. Moreover, the users tend to prefer models found using the proposed approach over models found using non-personalized interpretability indices.
Open AccessModel Learning with Personalized Interpretability Estimation (ML-PIE)
High-stakes applications require AI-generated models to be interpretable. Current algorithms for the synthesis of potentially interpretable models rely on objectives or regularization terms that represent interpretability only coarsely (e.g., model size) and are not designed for a specific user. Yet, interpretability is intrinsically subjective. In this paper, we propose an approach for the synthesis of models that are tailored to the user by enabling the user to steer the model synthesis process according to her or his preferences. We use a bi-objective evolutionary algorithm to synthesize models with trade-offs between accuracy and a user-specific notion of interpretability. The latter is estimated by a neural network that is trained concurrently to the evolution using the feedback of the user, which is collected using uncertainty-based active learning. To maximize usability, the user is only asked to tell, given two models at the time, which one is less complex. With experiments on two real-world datasets involving 61 participants, we find that our approach is capable of learning estimations of interpretability that can be very different for different users. Moreover, the users tend to prefer models found using the proposed approach over models found using non-personalized interpretability indices.
- 1 July 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
A Dialogue manager for task-oriented agents based on dialogue building-blocks and generic cognitive processing
This paper introduces a novel dialogue manager, called DAISY, for intelligent virtual agents. The proposed approach is based on two central concepts: (i) dialogue building-blocks, which offer a systematic approach to the representation and implementation of human-agent dialogue, and (ii) cognitive processing in the form of sequences of simple, generic cognitive actions. The generic nature of the cognitive actions makes it possible to represent a large variety of cognitive processing (e.g, retrieving and manipulating memory content) by using a rather small set of such actions. DAISY is illustrated by means of a specific example, namely an agent acting as an information system for travel and tourist information. The example highlights the usefulness of the systematic approach offered by DAISY.
- 1 July 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
A Dialogue manager for task-oriented agents based on dialogue building-blocks and generic cognitive processing
This paper introduces a novel dialogue manager, called DAISY, for intelligent virtual agents. The proposed approach is based on two central concepts: (i) dialogue building-blocks, which offer a systematic approach to the representation and implementation of human-agent dialogue, and (ii) cognitive processing in the form of sequences of simple, generic cognitive actions. The generic nature of the cognitive actions makes it possible to represent a large variety of cognitive processing (e.g, retrieving and manipulating memory content) by using a rather small set of such actions. DAISY is illustrated by means of a specific example, namely an agent acting as an information system for travel and tourist information. The example highlights the usefulness of the systematic approach offered by DAISY.