liu.seSearch for publications in DiVA
Change search
Link to record
Permanent link

Direct link
Kunz, Jenny
Publications (7 of 7) Show all publications
Braun, M. & Kunz, J. (2024). A Hypothesis-Driven Framework for the Analysis of Self-Rationalising Models. In: : . Paper presented at Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop (pp. 148-161).
Open this publication in new window or tab >>A Hypothesis-Driven Framework for the Analysis of Self-Rationalising Models
2024 (English)Conference paper, Published paper (Refereed)
National Category
Language Technology (Computational Linguistics)
Identifiers
urn:nbn:se:liu:diva-201911 (URN)
Conference
Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop
Available from: 2024-03-26 Created: 2024-03-26 Last updated: 2024-04-17
Kunz, J. & Holmström, O. (2024). The Impact of Language Adapters in Cross-Lingual Transfer for NLU. In: : . Paper presented at Proceedings of the 1st Workshop on Modular and Open Multilingual NLP (MOOMIN 2024) (pp. 24-43).
Open this publication in new window or tab >>The Impact of Language Adapters in Cross-Lingual Transfer for NLU
2024 (English)Conference paper, Published 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.

Keywords
Large Language Models, LLMs, Adapters, NLP
National Category
Language Technology (Computational Linguistics)
Identifiers
urn:nbn:se:liu:diva-201912 (URN)
Conference
Proceedings of the 1st Workshop on Modular and Open Multilingual NLP (MOOMIN 2024)
Available from: 2024-03-26 Created: 2024-03-26 Last updated: 2024-03-26
Kunz, J. (2024). Understanding Large Language Models: Towards Rigorous and Targeted Interpretability Using Probing Classifiers and Self-Rationalisation. (Doctoral dissertation). Linköping: Linköping University Electronic Press
Open this publication in new window or tab >>Understanding Large Language Models: Towards Rigorous and Targeted Interpretability Using Probing Classifiers and Self-Rationalisation
2024 (English)Doctoral 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. 

Place, publisher, year, edition, pages
Linköping: Linköping University Electronic Press, 2024. p. 81
Series
Linköping Studies in Science and Technology. Dissertations, ISSN 0345-7524 ; 2364
National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:liu:diva-201985 (URN)10.3384/9789180754712 (DOI)9789180754705 (ISBN)9789180754712 (ISBN)
Public defence
2024-04-18, Ada Lovelace, B-building, Campus Valla, Linköping, 14:00 (English)
Opponent
Supervisors
Available from: 2024-04-02 Created: 2024-04-02 Last updated: 2024-04-02Bibliographically approved
Holmström, O., Kunz, J. & Kuhlmann, M. (2023). Bridging the Resource Gap: Exploring the Efficacy of English and Multilingual LLMs for Swedish. In: Proceedings of the Second Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2023): . Paper presented at RESOURCEFUL workshop at NoDaLiDa (pp. 92-110). Tórshavn, the Faroe Islands
Open this publication in new window or tab >>Bridging the Resource Gap: Exploring the Efficacy of English and Multilingual LLMs for Swedish
2023 (English)In: 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, Published 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.

Place, publisher, year, edition, pages
Tórshavn, the Faroe Islands: , 2023
Keywords
NLP, Natural Language Processing, language model, GPT, monolingual, multilingual, cross-lingual, one model-many models
National Category
Language Technology (Computational Linguistics)
Identifiers
urn:nbn:se:liu:diva-196545 (URN)
Conference
RESOURCEFUL workshop at NoDaLiDa
Funder
CUGS (National Graduate School in Computer Science)
Available from: 2023-08-11 Created: 2023-08-11 Last updated: 2023-08-11
Kunz, J., Jirénius, M., Holmström, O. & Kuhlmann, M. (2022). Human Ratings Do Not Reflect Downstream Utility: A Study of Free-Text Explanations for Model Predictions. In: Proceedings of the Fifth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP: . Paper presented at BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, December 8, 2022 (pp. 164-177). , 5, Article ID 2022.blackboxnlp-1.14.
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
Kunz, J. & Kuhlmann, M. (2022). Where Does Linguistic Information Emerge in Neural Language Models?: Measuring Gains and Contributions across Layers. In: 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 (Ed.), Proceedings of the 29th International Conference on Computational Linguistics: . Paper presented at COLING, October 12–17, 2022 (pp. 4664-4676). , Article ID 1.413.
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
Kunz, J. & Kuhlmann, M. (2021). Test Harder Than You Train: Probing with Extrapolation Splits. In: Jasmijn Bastings, Yonatan Belinkov, Emmanuel Dupoux, Mario Giulianelli, Dieuwke Hupkes, Yuval Pinter, Hassan Sajjad (Ed.), Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP: . Paper presented at BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, November 11, 2021 (pp. 15-25). Punta Cana, Dominican Republic, 5, Article ID 2.
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
Organisations

Search in DiVA

Show all publications