Profiles2020-2026
Anders Søgaard
University of Copenhagen
26Papers
19Last author
36Unique co-authors
1First author
1Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers26
- FrameNet-Cultures: A Benchmark for Evaluating LLMs via Cross-Cultural Frame SemanticsAuthor 2 of 3ACL Findings 2026
- Lost in Embeddings: Information Loss in Vision-Language ModelsAuthor 6 of 6EMNLP Findings 2025 · 1 citation
- Understanding Subword Compositionality of Large Language ModelsAuthor 3 of 3EMNLP 2025
- What if Othello-Playing Language Models Could See?Author 6 of 6EMNLP Findings 2025
- Unlocking Markets: A Multilingual Benchmark to Cross-Market Question AnsweringAuthor 3 of 4EMNLP 2024
- Mapping Brains with Language Models: A SurveyAuthor 3 of 3ACL Findings 2023 · 13 citations
- Being Right for Whose Right Reasons?Author 4 of 4ACL 2023 · 8 citations
- What does the Failure to Reason with "Respectively" in Zero/Few-Shot Settings Tell Us about Language Models?Author 4 of 4ACL 2023 · 1 citation
- Square One Bias in NLP: Towards a Multi-Dimensional Exploration of the Research ManifoldAuthor 3 of 3ACL Findings 2022 · 21 citations
- Factual Consistency of Multilingual Pretrained Language ModelsAuthor 2 of 2ACL Findings 2022 · 16 citations
- Do Transformer Models Show Similar Attention Patterns to Task-Specific Human Gaze?Author 4 of 4ACL 2022
- Word Order Does Matter and Shuffled Language Models Know ItAuthor 4 of 4ACL 2022
- Analogy Training Multilingual EncodersAuthor 6 of 6AAAI 2021 · 17 citations
- On the Interaction of Belief Bias and ExplanationsAuthor 3 of 3ACL Findings 2021 · 10 citations
- The Impact of Positional Encodings on Multilingual CompressionAuthor 2 of 2EMNLP 2021 · 7 citations
- Is the Lottery Fair? Evaluating Winning Tickets Across DemographicsAuthor 3 of 3ACL Findings 2021 · 4 citations
- Joint Semantic Analysis with Document-Level Cross-Task Coherence RewardsAuthor 5 of 5AAAI 2021 · 2 citations
- John praised Mary because he? Implicit Causality Bias and Its Interaction with Explicit Cues in LMsAuthor 3 of 3ACL Findings 2021 · 1 citation
- Minimax and Neyman-Pearson Meta-Learning for Outlier LanguagesAuthor 5 of 5ACL Findings 2021
- Parsing as PretrainingAuthor 3 of 4AAAI 2020 · 33 citations
- Weakly Supervised POS Taggers Perform Poorly on Truly Low-Resource LanguagesAuthor 3 of 3AAAI 2020 · 21 citations
- What Do You Mean 'Why?': Resolving Sluices in ConversationsAuthor 3 of 4AAAI 2020 · 11 citations
- Are All Good Word Vector Spaces Isomorphic?Author 3 of 4EMNLP 2020 · 7 citations
- Neural Speed Reading AuditedAuthor 1 of 1EMNLP Findings 2020 · 2 citations
- Grammatical Error Correction in Low Error Density Domains: A New Benchmark and AnalysesAuthor 5 of 5EMNLP 2020
- Type B Reflexivization as an Unambiguous Testbed for Multilingual Multi-Task Gender BiasAuthor 5 of 6EMNLP 2020
