liu.seSearch for publications in DiVA
Change search
Refine search result
1 - 7 of 7
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Rows per page
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sort
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
Select
The maximal number of hits you can export is 250. When you want to export more records please use the Create feeds function.
  • 1.
    Braun, Marc
    et al.
    Linköping University, Department of Computer and Information Science, Artificial Intelligence and Integrated Computer Systems. Linköping University, Faculty of Science & Engineering. University of Stuttgart, Fraunhofer IPA.
    Kunz, Jenny
    Linköping University, Department of Computer and Information Science, Artificial Intelligence and Integrated Computer Systems. Linköping University, Faculty of Science & Engineering.
    A Hypothesis-Driven Framework for the Analysis of Self-Rationalising Models2024Conference paper (Refereed)
  • 2.
    Holmström, Oskar
    et al.
    Linköping University, Department of Computer and Information Science, Artificial Intelligence and Integrated Computer Systems. Linköping University, Faculty of Science & Engineering.
    Kunz, Jenny
    Linköping University, Department of Computer and Information Science, Artificial Intelligence and Integrated Computer Systems. Linköping University, Faculty of Science & Engineering.
    Kuhlmann, Marco
    Linköping University, Department of Computer and Information Science, Human-Centered systems. Linköping University, Faculty of Science & Engineering. Linköping University, Department of Computer and Information Science, Artificial Intelligence and Integrated Computer Systems.
    Bridging the Resource Gap: Exploring the Efficacy of English and Multilingual LLMs for Swedish2023In: Proceedings of the Second Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2023), Tórshavn, the Faroe Islands, 2023, p. 92-110Conference paper (Refereed)
    Abstract [en]

    Large language models (LLMs) have substantially improved natural language processing (NLP) performance, but training these models from scratch is resource-intensive and challenging for smaller languages. With this paper, we want to initiate a discussion on the necessity of language-specific pre-training of LLMs. We propose how the “one model-many models” conceptual framework for task transfer can be applied to language transfer and explore this approach by evaluating the performance of non-Swedish monolingual and multilingual models’ performance on tasks in Swedish. Our findings demonstrate that LLMs exposed to limited Swedish during training can be highly capable and transfer competencies from English off-the-shelf, including emergent abilities such as mathematical reasoning, while at the same time showing distinct culturally adapted behaviour. Our results suggest that there are resourceful alternatives to language-specific pre-training when creating useful LLMs for small languages.

  • 3. Order onlineBuy this publication >>
    Kunz, Jenny
    Linköping University, Department of Computer and Information Science, Artificial Intelligence and Integrated Computer Systems. Linköping University, Faculty of Science & Engineering.
    Understanding Large Language Models: Towards Rigorous and Targeted Interpretability Using Probing Classifiers and Self-Rationalisation2024Doctoral thesis, comprehensive summary (Other academic)
    Abstract [en]

    Large language models (LLMs) have become the base of many natural language processing (NLP) systems due to their performance and easy adaptability to various tasks. However, much about their inner workings is still unknown. LLMs have many millions or billions of parameters, and large parts of their training happen in a self-supervised fashion: They simply learn to predict the next word, or missing words, in a sequence. This is effective for picking up a wide range of linguistic, factual and relational information, but it implies that it is not trivial what exactly is learned, and how it is represented within the LLM. 

    In this thesis, I present our work on methods contributing to better understanding LLMs. The work can be grouped into two approaches. The first lies within the field of interpretability, which is concerned with understanding the internal workings of the LLMs. Specifically, we analyse and refine a tool called probing classifiers that inspects the intermediate representations of LLMs, focusing on what roles the various layers of the neural model play. This helps us to get a global understanding of how information is structured in the model. I present our work on assessing and improving the probing methodologies. We developed a framework to clarify the limitations of past methods, showing that all common controls are insufficient. Based on this, we proposed more restrictive probing setups by creating artificial distribution shifts. We developed new metrics for the evaluation of probing classifiers that move the focus from the overall information that the layer contains to differences in information content across the LLM. 

    The second approach is concerned with explainability, specifically with self-rationalising models that generate free-text explanations along with their predictions. This is an instance of local understandability: We obtain justifications for individual predictions. In this setup, however, the generation of the explanations is just as opaque as the generation of the predictions. Therefore, our work in this field focuses on better understanding the properties of the generated explanations. We evaluate the downstream performance of a classifier with explanations generated by different model pipelines and compare it to human ratings of the explanations. Our results indicate that the properties that increase the downstream performance differ from those that humans appreciate when evaluating an explanation. Finally, we annotate explanations generated by an LLM for properties that human explanations typically have and discuss the effects those properties have on different user groups. 

    While a detailed understanding of the inner workings of LLMs is still unfeasible, I argue that the techniques and analyses presented in this work can help to better understand LLMs, the linguistic knowledge they encode and their decision-making process. Together with knowledge about the models’ architecture, training data and training objective, such techniques can help us develop a robust high-level understanding of LLMs that can guide decisions on their deployment and potential improvements. 

    List of papers
    1. Classifier Probes May Just Learn from Linear Context Features
    Open this publication in new window or tab >>Classifier Probes May Just Learn from Linear Context Features
    2020 (English)In: Proceedings of the 28th International Conference on Computational Linguistics, 2020, Vol. 28, p. 5136-5146, article id 450Conference paper, Published paper (Refereed)
    Abstract [en]

    Classifiers trained on auxiliary probing tasks are a popular tool to analyze the representations learned by neural sentence encoders such as BERT and ELMo. While many authors are aware of the difficulty to distinguish between “extracting the linguistic structure encoded in the representations” and “learning the probing task,” the validity of probing methods calls for further research. Using a neighboring word identity prediction task, we show that the token embeddings learned by neural sentence encoders contain a significant amount of information about the exact linear context of the token, and hypothesize that, with such information, learning standard probing tasks may be feasible even without additional linguistic structure. We develop this hypothesis into a framework in which analysis efforts can be scrutinized and argue that, with current models and baselines, conclusions that representations contain linguistic structure are not well-founded. Current probing methodology, such as restricting the classifier’s expressiveness or using strong baselines, can help to better estimate the complexity of learning, but not build a foundation for speculations about the nature of the linguistic structure encoded in the learned representations.

    Keywords
    Natural Language Processing, Machine Learning, Neural Language Representations
    National Category
    Language Technology (Computational Linguistics) Computer Sciences
    Identifiers
    urn:nbn:se:liu:diva-175384 (URN)10.18653/v1/2020.coling-main.450 (DOI)
    Conference
    International Conference on Computational Linguistics (COLING), Barcelona, Spain (Online), December 8–13, 2020
    Available from: 2021-04-30 Created: 2021-04-30 Last updated: 2024-04-02Bibliographically approved
    2. Test Harder Than You Train: Probing with Extrapolation Splits
    Open this publication in new window or tab >>Test Harder Than You Train: Probing with Extrapolation Splits
    2021 (English)In: Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP / [ed] Jasmijn Bastings, Yonatan Belinkov, Emmanuel Dupoux, Mario Giulianelli, Dieuwke Hupkes, Yuval Pinter, Hassan Sajjad, Punta Cana, Dominican Republic, 2021, Vol. 5, p. 15-25, article id 2Conference paper, Published paper (Refereed)
    Abstract [en]

    Previous work on probing word representations for linguistic knowledge has focused on interpolation tasks. In this paper, we instead analyse probes in an extrapolation setting, where the inputs at test time are deliberately chosen to be ‘harder’ than the training examples. We argue that such an analysis can shed further light on the open question whether probes actually decode linguistic knowledge, or merely learn the diagnostic task from shallow features. To quantify the hardness of an example, we consider scoring functions based on linguistic, statistical, and learning-related criteria, all of which are applicable to a broad range of NLP tasks. We discuss the relative merits of these criteria in the context of two syntactic probing tasks, part-of-speech tagging and syntactic dependency labelling. From our theoretical and experimental analysis, we conclude that distance-based and hard statistical criteria show the clearest differences between interpolation and extrapolation settings, while at the same time being transparent, intuitive, and easy to control.

    Place, publisher, year, edition, pages
    Punta Cana, Dominican Republic: , 2021
    Keywords
    Natural Language Processing, Neural Language Models, Interpretability, Probing, BERT, Extrapolation
    National Category
    Language Technology (Computational Linguistics) Computer Sciences
    Identifiers
    urn:nbn:se:liu:diva-182166 (URN)10.18653/v1/2021.blackboxnlp-1.2 (DOI)
    Conference
    BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, November 11, 2021
    Available from: 2022-01-10 Created: 2022-01-10 Last updated: 2024-04-02Bibliographically approved
    3. Where Does Linguistic Information Emerge in Neural Language Models?: Measuring Gains and Contributions across Layers
    Open this publication in new window or tab >>Where Does Linguistic Information Emerge in Neural Language Models?: Measuring Gains and Contributions across Layers
    2022 (English)In: Proceedings of the 29th International Conference on Computational Linguistics / [ed] Nicoletta Calzolari, Chu-Ren Huang, Hansaem Kim, James Pustejovsky, Leo Wanner, Key-Sun Choi, Pum-Mo Ryu, Hsin-Hsi Chen, Lucia Donatelli, Heng Ji, Sadao Kurohashi, Patrizia Paggio, Nianwen Xue, Seokhwan Kim, Younggyun Hahm, Zhong He, Tony Kyungil Lee, Enrico Santus, Francis Bond, Seung-Hoon Na, 2022, p. 4664-4676, article id 1.413Conference paper, Published paper (Refereed)
    Abstract [en]

    Probing studies have extensively explored where in neural language models linguistic information is located. The standard approach to interpreting the results of a probing classifier is to focus on the layers whose representations give the highest performance on the probing task. We propose an alternative method that asks where the task-relevant information emerges in the model. Our framework consists of a family of metrics that explicitly model local information gain relative to the previous layer and each layer’s contribution to the model’s overall performance. We apply the new metrics to two pairs of syntactic probing tasks with different degrees of complexity and find that the metrics confirm the expected ordering only for one of the pairs. Our local metrics show a massive dominance of the first layers, indicating that the features that contribute the most to our probing tasks are not as high-level as global metrics suggest.

    Keywords
    NLP, AI, Language Technology, Computational Linguistics, Machine Learning
    National Category
    Language Technology (Computational Linguistics)
    Identifiers
    urn:nbn:se:liu:diva-191000 (URN)
    Conference
    COLING, October 12–17, 2022
    Available from: 2023-01-12 Created: 2023-01-12 Last updated: 2024-05-23Bibliographically approved
    4. Human Ratings Do Not Reflect Downstream Utility: A Study of Free-Text Explanations for Model Predictions
    Open this publication in new window or tab >>Human Ratings Do Not Reflect Downstream Utility: A Study of Free-Text Explanations for Model Predictions
    2022 (English)In: Proceedings of the Fifth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, 2022, Vol. 5, p. 164-177, article id 2022.blackboxnlp-1.14Conference paper, Published paper (Refereed)
    Abstract [en]

    Models able to generate free-text rationales that explain their output have been proposed as an important step towards interpretable NLP for “reasoning” tasks such as natural language inference and commonsense question answering. However, the relative merits of different architectures and types of rationales are not well understood and hard to measure. In this paper, we contribute two insights to this line of research: First, we find that models trained on gold explanations learn to rely on these but, in the case of the more challenging question answering data set we use, fail when given generated explanations at test time. However, additional fine-tuning on generated explanations teaches the model to distinguish between reliable and unreliable information in explanations. Second, we compare explanations by a generation-only model to those generated by a self-rationalizing model and find that, while the former score higher in terms of validity, factual correctness, and similarity to gold explanations, they are not more useful for downstream classification. We observe that the self-rationalizing model is prone to hallucination, which is punished by most metrics but may add useful context for the classification step.

    Keywords
    Large Language Models, Neural Networks, Transformers, Interpretability, Explainability
    National Category
    Language Technology (Computational Linguistics) Computer Sciences
    Identifiers
    urn:nbn:se:liu:diva-195615 (URN)
    Conference
    BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, December 8, 2022
    Available from: 2023-06-22 Created: 2023-06-22 Last updated: 2024-04-02Bibliographically approved
    Download full text (pdf)
    fulltext
    Download (png)
    presentationsbild
  • 4.
    Kunz, Jenny
    et al.
    Linköping University, Department of Computer and Information Science, Artificial Intelligence and Integrated Computer Systems. Linköping University, Faculty of Science & Engineering.
    Holmström, Oskar
    Linköping University, Department of Computer and Information Science, Artificial Intelligence and Integrated Computer Systems. Linköping University, Faculty of Science & Engineering.
    The Impact of Language Adapters in Cross-Lingual Transfer for NLU2024Conference paper (Refereed)
    Abstract [en]

    Modular deep learning has been proposed for the efficient adaption of pre-trained models to new tasks, domains and languages. In particular, combining language adapters with task adapters has shown potential where no supervised data exists for a language. In this paper, we explore the role of language adapters in zero-shot cross-lingual transfer for natural language understanding (NLU) benchmarks. We study the effect of including a target-language adapter in detailed ablation studies with two multilingual models and three multilingual datasets. Our results show that the effect of target-language adapters is highly inconsistent across tasks, languages and models. Retaining the source-language adapter instead often leads to an equivalent, and sometimes to a better, performance. Removing the language adapter after training has only a weak negative effect, indicating that the language adapters do not have a strong impact on the predictions.

  • 5.
    Kunz, Jenny
    et al.
    Linköping University, Department of Computer and Information Science, Artificial Intelligence and Integrated Computer Systems. Linköping University, Faculty of Science & Engineering.
    Jirénius, Martin
    Linköping University, Department of Computer and Information Science. Linköping University, Faculty of Science & Engineering.
    Holmström, Oskar
    Linköping University, Department of Computer and Information Science, Artificial Intelligence and Integrated Computer Systems. Linköping University, Faculty of Science & Engineering.
    Kuhlmann, Marco
    Linköping University, Department of Computer and Information Science, Artificial Intelligence and Integrated Computer Systems. Linköping University, Faculty of Science & Engineering.
    Human Ratings Do Not Reflect Downstream Utility: A Study of Free-Text Explanations for Model Predictions2022In: Proceedings of the Fifth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, 2022, Vol. 5, p. 164-177, article id 2022.blackboxnlp-1.14Conference paper (Refereed)
    Abstract [en]

    Models able to generate free-text rationales that explain their output have been proposed as an important step towards interpretable NLP for “reasoning” tasks such as natural language inference and commonsense question answering. However, the relative merits of different architectures and types of rationales are not well understood and hard to measure. In this paper, we contribute two insights to this line of research: First, we find that models trained on gold explanations learn to rely on these but, in the case of the more challenging question answering data set we use, fail when given generated explanations at test time. However, additional fine-tuning on generated explanations teaches the model to distinguish between reliable and unreliable information in explanations. Second, we compare explanations by a generation-only model to those generated by a self-rationalizing model and find that, while the former score higher in terms of validity, factual correctness, and similarity to gold explanations, they are not more useful for downstream classification. We observe that the self-rationalizing model is prone to hallucination, which is punished by most metrics but may add useful context for the classification step.

  • 6.
    Kunz, Jenny
    et al.
    Linköping University, Department of Computer and Information Science, Artificial Intelligence and Integrated Computer Systems. Linköping University, Faculty of Science & Engineering.
    Kuhlmann, Marco
    Linköping University, Department of Computer and Information Science, Artificial Intelligence and Integrated Computer Systems. Linköping University, Faculty of Science & Engineering.
    Test Harder Than You Train: Probing with Extrapolation Splits2021In: Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP / [ed] Jasmijn Bastings, Yonatan Belinkov, Emmanuel Dupoux, Mario Giulianelli, Dieuwke Hupkes, Yuval Pinter, Hassan Sajjad, Punta Cana, Dominican Republic, 2021, Vol. 5, p. 15-25, article id 2Conference paper (Refereed)
    Abstract [en]

    Previous work on probing word representations for linguistic knowledge has focused on interpolation tasks. In this paper, we instead analyse probes in an extrapolation setting, where the inputs at test time are deliberately chosen to be ‘harder’ than the training examples. We argue that such an analysis can shed further light on the open question whether probes actually decode linguistic knowledge, or merely learn the diagnostic task from shallow features. To quantify the hardness of an example, we consider scoring functions based on linguistic, statistical, and learning-related criteria, all of which are applicable to a broad range of NLP tasks. We discuss the relative merits of these criteria in the context of two syntactic probing tasks, part-of-speech tagging and syntactic dependency labelling. From our theoretical and experimental analysis, we conclude that distance-based and hard statistical criteria show the clearest differences between interpolation and extrapolation settings, while at the same time being transparent, intuitive, and easy to control.

    Download full text (pdf)
    fulltext
  • 7.
    Kunz, Jenny
    et al.
    Linköping University, Department of Computer and Information Science, Artificial Intelligence and Integrated Computer Systems. Linköping University, Faculty of Science & Engineering.
    Kuhlmann, Marco
    Linköping University, Department of Computer and Information Science, Artificial Intelligence and Integrated Computer Systems. Linköping University, Faculty of Science & Engineering.
    Where Does Linguistic Information Emerge in Neural Language Models?: Measuring Gains and Contributions across Layers2022In: Proceedings of the 29th International Conference on Computational Linguistics / [ed] Nicoletta Calzolari, Chu-Ren Huang, Hansaem Kim, James Pustejovsky, Leo Wanner, Key-Sun Choi, Pum-Mo Ryu, Hsin-Hsi Chen, Lucia Donatelli, Heng Ji, Sadao Kurohashi, Patrizia Paggio, Nianwen Xue, Seokhwan Kim, Younggyun Hahm, Zhong He, Tony Kyungil Lee, Enrico Santus, Francis Bond, Seung-Hoon Na, 2022, p. 4664-4676, article id 1.413Conference paper (Refereed)
    Abstract [en]

    Probing studies have extensively explored where in neural language models linguistic information is located. The standard approach to interpreting the results of a probing classifier is to focus on the layers whose representations give the highest performance on the probing task. We propose an alternative method that asks where the task-relevant information emerges in the model. Our framework consists of a family of metrics that explicitly model local information gain relative to the previous layer and each layer’s contribution to the model’s overall performance. We apply the new metrics to two pairs of syntactic probing tasks with different degrees of complexity and find that the metrics confirm the expected ordering only for one of the pairs. Our local metrics show a massive dominance of the first layers, indicating that the features that contribute the most to our probing tasks are not as high-level as global metrics suggest.

    Download full text (pdf)
    fulltext
1 - 7 of 7
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf