 Mechanistic Interpretability of Emotion Inference in Large Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL), 2025 |
 Gumbel Counterfactual Generation From Language ModelsInternational Conference on Learning Representations (ICLR), 2024 |
 Layer by Layer: Uncovering Where Multi-Task Learning Happens in
Instruction-Tuned Large Language ModelsConference on Empirical Methods in Natural Language Processing (EMNLP), 2024 |
 Can Language Models Induce Grammatical Knowledge from Indirect Evidence?Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024 |
 Mechanistic?BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackBoxNLP), 2024 |
 How Language Models Prioritize Contextual Grammatical Cues?BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackBoxNLP), 2024 |
 Linguistic Minimal Pairs Elicit Linguistic Similarity in Large Language
ModelsInternational Conference on Computational Linguistics (COLING), 2024 |
 Recurrent Neural Networks Learn to Store and Generate Sequences using
Non-Linear RepresentationsBlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackBoxNLP), 2024 |
 |
 Grammatical information in BERT sentence embeddings as two-dimensional
arraysWorkshop on Representation Learning for NLP (RepL4NLP), 2023 |
 Codebook Features: Sparse and Discrete Interpretability for Neural
NetworksInternational Conference on Machine Learning (ICML), 2023 |
 Subspace Chronicles: How Linguistic Information Emerges, Shifts and
Interacts during Language Model TrainingConference on Empirical Methods in Natural Language Processing (EMNLP), 2023 |
 Unnatural language processing: How do language models handle
machine-generated prompts?Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023 |
 Verb Conjugation in Transformers Is Determined by Linear Encodings of
Subject NumberConference on Empirical Methods in Natural Language Processing (EMNLP), 2023 |
 Investigating semantic subspaces of Transformer sentence embeddings
through linear structural probingBlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP), 2023 |
 Emergent Linear Representations in World Models of Self-Supervised
Sequence ModelsBlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP), 2023 |
 Operationalising Representation in Natural Language ProcessingBritish Journal for the Philosophy of Science (BJPS), 2023 |
 How does GPT-2 compute greater-than?: Interpreting mathematical
abilities in a pre-trained language modelNeural Information Processing Systems (NeurIPS), 2023 |
 Interventional Probing in High Dimensions: An NLI Case StudyFindings (Findings), 2023 |
 An Overview on Language Models: Recent Developments and OutlookAPSIPA Transactions on Signal and Information Processing (TASIP), 2023 |
 Reconstruction ProbingAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 |
 Assessing the Capacity of Transformer to Abstract Syntactic
Representations: A Contrastive Analysis Based on Long-distance AgreementTransactions of the Association for Computational Linguistics (TACL), 2022 |
 Understanding Domain Learning in Language Models Through Subpopulation
AnalysisBlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP), 2022 |
 Probing with Noise: Unpicking the Warp and Weft of EmbeddingsBlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP), 2022 |
 State-of-the-art generalisation research in NLP: A taxonomy and reviewNature Machine Intelligence (Nat. Mach. Intell.), 2022 |
 Probing via PromptingNorth American Chapter of the Association for Computational Linguistics (NAACL), 2022 |
 Naturalistic Causal Probing for Morpho-SyntaxTransactions of the Association for Computational Linguistics (TACL), 2022 |
 When Does Syntax Mediate Neural Language Model Performance? Evidence
from Dropout ProbesNorth American Chapter of the Association for Computational Linguistics (NAACL), 2022 |
