Benjamin Heinzerling

54 papers A* 3A 1B 3Journal 28Unranked 18

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	Can Language Models Handle a Non-Gregorian Calendar? CoRR Mutsumi Sasaki, Go Kamoda, Ryosuke Takahashi, Kosuke Sato, Kentaro Inui, Keisuke Sakaguchi, Benjamin Heinzerling
2025	—	`conf`	Can Language Models Handle a Non-Gregorian Calendar? The Case of the Japanese wareki. IJCNLP-AACL (Short Papers) Mutsumi Sasaki, Go Kamoda, Ryosuke Takahashi, Kosuke Sato, Kentaro Inui, Keisuke Sakaguchi, Benjamin Heinzerling
2025	J	`jnl`	Do LLMs Need to Think in One Language? Correlation between Latent Language and Task Performance. CoRR Shintaro Ozaki, Tatsuya Hiraoka, Hiroto Otake, Hiroki Ouchi, Masaru Isonuma, Benjamin Heinzerling, Kentaro Inui, Taro Watanabe, Yusuke Miyao, Yohei Oseki, Yu Takagi
2025	J	`jnl`	How LLMs Learn: Tracing Internal Representations with Sparse Autoencoders. CoRR Tatsuro Inaba, Kentaro Inui, Yusuke Miyao, Yohei Oseki, Benjamin Heinzerling, Yu Takagi
2025	—	`conf`	How a Bilingual LM Becomes Bilingual: Tracing Internal Representations with Sparse Autoencoders. EMNLP (Findings) Tatsuro Inaba, Go Kamoda, Kentaro Inui, Masaru Isonuma, Yusuke Miyao, Yohei Oseki, Yu Takagi, Benjamin Heinzerling
2025	—	`conf`	Library-Like Behavior In Language Models is Enhanced by Self-Referencing Causal Cycles. ACL (1) Munachiso Nwadike, Zangir Iklassov, Toluwani Aremu, Tatsuya Hiraoka, Benjamin Heinzerling, Velibor Bojkovic, Hilal AlQuabeh, Martin Takác, Kentaro Inui
2025	—	`conf`	On Entity Identification in Language Models. ACL (Findings) Masaki Sakata, Benjamin Heinzerling, Sho Yokoi, Takumi Ito, Kentaro Inui
2025	J	`jnl`	On Entity Identification in Language Models. CoRR Masaki Sakata, Benjamin Heinzerling, Sho Yokoi, Takumi Ito, Kentaro Inui
2025	J	`jnl`	RECALL: Library-Like Behavior In Language Models is Enhanced by Self-Referencing Causal Cycles. CoRR Munachiso Nwadike, Zangir Iklassov, Toluwani Aremu, Tatsuya Hiraoka, Velibor Bojkovic, Benjamin Heinzerling, Hilal Alqaubeh, Martin Takác, Kentaro Inui
2025	—	`conf`	The Geometry of Numerical Reasoning: Language Models Compare Numeric Properties in Linear Subspaces. NAACL (Short Papers) Ahmed Oumar El-Shangiti, Tatsuya Hiraoka, Hilal AlQuabeh, Benjamin Heinzerling, Kentaro Inui
2025	J	`jnl`	TopK Language Models. CoRR Ryosuke Takahashi, Tatsuro Inaba, Kentaro Inui, Benjamin Heinzerling
2025	J	`jnl`	Understanding Fact Recall in Language Models: Why Two-Stage Training Encourages Memorization but Mixed Training Teaches Knowledge. CoRR Ying Zhang, Benjamin Heinzerling, Dongyuan Li, Ryoma Ishigaki, Yuta Hitomi, Kentaro Inui
2025	—	`conf`	Weight-based Analysis of Detokenization in Language Models: Understanding the First Stage of Inference Without Inference. NAACL (Findings) Go Kamoda, Benjamin Heinzerling, Tatsuro Inaba, Keito Kudo, Keisuke Sakaguchi, Kentaro Inui
2025	J	`jnl`	Weight-based Analysis of Detokenization in Language Models: Understanding the First Stage of Inference Without Inference. CoRR Go Kamoda, Benjamin Heinzerling, Tatsuro Inaba, Keito Kudo, Keisuke Sakaguchi, Kentaro Inui
2024	J	`jnl`	ACORN: Aspect-wise Commonsense Reasoning Explanation Evaluation. CoRR Ana Brassard, Benjamin Heinzerling, Keito Kudo, Keisuke Sakaguchi, Kentaro Inui
2024	—	`conf`	Monotonic Representation of Numeric Attributes in Language Models. ACL (Short Papers) Benjamin Heinzerling, Kentaro Inui
2024	J	`jnl`	Monotonic Representation of Numeric Properties in Language Models. CoRR Benjamin Heinzerling, Kentaro Inui
2024	A*	`conf`	Representational Analysis of Binding in Language Models. EMNLP Qin Dai, Benjamin Heinzerling, Kentaro Inui
2024	J	`jnl`	Representational Analysis of Binding in Large Language Models. CoRR Qin Dai, Benjamin Heinzerling, Kentaro Inui
2024	J	`jnl`	The Curse of Popularity: Popular Entities have Catastrophic Side Effects when Deleting Knowledge from Language Models. CoRR Ryosuke Takahashi, Go Kamoda, Benjamin Heinzerling, Keisuke Sakaguchi, Kentaro Inui
2024	J	`jnl`	The Geometry of Numerical Reasoning: Language Models Compare Numeric Properties in Linear Subspaces. CoRR Ahmed Oumar El-Shangiti, Tatsuya Hiraoka, Hilal AlQuabeh, Benjamin Heinzerling, Kentaro Inui
2023	—	`conf`	Can LMs Store and Retrieve 1-to-N Relational Knowledge? ACL (student) Haruki Nagasawa, Benjamin Heinzerling, Kazuma Kokuta, Kentaro Inui
2023	J	`jnl`	Examining the effect of whitening on static and contextualized word embeddings. Inf. Process. Manag. Shota Sasaki, Benjamin Heinzerling, Jun Suzuki, Kentaro Inui
2023	—	`conf`	Prompting for explanations improves Adversarial NLI. Is this true? Yes it is true because it weakens superficial cues. EACL (Findings) Pride Kavumba, Ana Brassard, Benjamin Heinzerling, Kentaro Inui
2023	—	`conf`	Test-time Augmentation for Factual Probing. EMNLP (Findings) Go Kamoda, Benjamin Heinzerling, Keisuke Sakaguchi, Kentaro Inui
2023	J	`jnl`	Test-time Augmentation for Factual Probing. CoRR Go Kamoda, Benjamin Heinzerling, Keisuke Sakaguchi, Kentaro Inui
2023	J	`jnl`	Tracing and Manipulating Intermediate Results in Neural Math Problem Solvers. J. Nat. Lang. Process. Yuta Matsumoto, Benjamin Heinzerling, Masashi Yoshikawa, Kentaro Inui
2023	J	`jnl`	Tracing and Manipulating Intermediate Values in Neural Math Problem Solvers. CoRR Yuta Matsumoto, Benjamin Heinzerling, Masashi Yoshikawa, Kentaro Inui
2022	B	`conf`	COPA-SSE: Semi-structured Explanations for Commonsense Reasoning. LREC Ana Brassard, Benjamin Heinzerling, Pride Kavumba, Kentaro Inui
2022	J	`jnl`	COPA-SSE: Semi-structured Explanations for Commonsense Reasoning. CoRR Ana Brassard, Benjamin Heinzerling, Pride Kavumba, Kentaro Inui
2022	A*	`conf`	Cross-stitching Text and Knowledge Graph Encoders for Distantly Supervised Relation Extraction. EMNLP Qin Dai, Benjamin Heinzerling, Kentaro Inui
2022	J	`jnl`	Cross-stitching Text and Knowledge Graph Encoders for Distantly Supervised Relation Extraction. CoRR Qin Dai, Benjamin Heinzerling, Kentaro Inui
2021	A	`conf`	Language Models as Knowledge Bases: On Entity Representations, Storage Capacity, and Paraphrased Queries. EACL Benjamin Heinzerling, Kentaro Inui
2021	—	`conf`	Learning to Learn to be Right for the Right Reasons. NAACL-HLT Pride Kavumba, Benjamin Heinzerling, Ana Brassard, Kentaro Inui
2021	J	`jnl`	Learning to Learn to be Right for the Right Reasons. CoRR Pride Kavumba, Benjamin Heinzerling, Ana Brassard, Kentaro Inui
2020	J	`jnl`	Language Models as Knowledge Bases: On Entity Representations, Storage Capacity, and Paraphrased Queries. CoRR Benjamin Heinzerling, Kentaro Inui
2019	—	`—`	Aspects of Coherence for Entity Analysis Benjamin Heinzerling
2019	—	`conf`	Fine-Grained Entity Typing in Hyperbolic Space. RepL4NLP@ACL Federico López, Benjamin Heinzerling, Michael Strube
2019	J	`jnl`	Fine-Grained Entity Typing in Hyperbolic Space. CoRR Federico López, Benjamin Heinzerling, Michael Strube
2019	B	`conf`	On the Importance of Subword Information for Morphological Tasks in Truly Low-Resource Languages. CoNLL Yi Zhu, Benjamin Heinzerling, Ivan Vulic, Michael Strube, Roi Reichart, Anna Korhonen
2019	J	`jnl`	On the Importance of Subword Information for Morphological Tasks in Truly Low-Resource Languages. CoRR Yi Zhu, Benjamin Heinzerling, Ivan Vulic, Michael Strube, Roi Reichart, Anna Korhonen
2019	J	`jnl`	Riposte! A Large Corpus of Counter-Arguments. CoRR Paul Reisert, Benjamin Heinzerling, Naoya Inoue, Shun Kiyono, Kentaro Inui
2019	—	`conf`	Sequence Tagging with Contextual and Non-Contextual Subword Representations: A Multilingual Evaluation. ACL (1) Benjamin Heinzerling, Michael Strube
2019	J	`jnl`	Sequence Tagging with Contextual and Non-Contextual Subword Representations: A Multilingual Evaluation. CoRR Benjamin Heinzerling, Michael Strube
2019	J	`jnl`	When Choosing Plausible Alternatives, Clever Hans can be Clever. CoRR Pride Kavumba, Naoya Inoue, Benjamin Heinzerling, Keshav Singh, Paul Reisert, Kentaro Inui
2018	B	`conf`	BPEmb: Tokenization-free Pre-trained Subword Embeddings in 275 Languages. LREC Benjamin Heinzerling, Michael Strube
2018	—	`conf`	What's Important in a Text? An Extensive Evaluation of Linguistic Annotations for Summarization. SNAMS Markus Zopf, Teresa Botschen, Tobias Falke, Benjamin Heinzerling, Ana Marasovic, Todor Mihaylov, Avinesh P. V. S., Eneldo Loza Mencía, Johannes Fürnkranz, Anette Frank
2017	J	`jnl`	BPEmb: Tokenization-free Pre-trained Subword Embeddings in 275 Languages. CoRR Benjamin Heinzerling, Michael Strube
2017	A*	`conf`	Revisiting Selectional Preferences for Coreference Resolution. EMNLP Benjamin Heinzerling, Nafise Sadat Moosavi, Michael Strube
2017	J	`jnl`	Revisiting Selectional Preferences for Coreference Resolution. CoRR Benjamin Heinzerling, Nafise Sadat Moosavi, Michael Strube
2017	—	`conf`	Trust, but Verify! Better Entity Linking through Automatic Verification. EACL (1) Benjamin Heinzerling, Michael Strube, Chin-Yew Lin
2015	—	`conf`	HITS at TAC KBP 2015: Entity Discovery and Linking, and Event Nugget Detection. TAC Benjamin Heinzerling, Alex Judea, Michael Strube
2015	—	`conf`	Visual Error Analysis for Entity Linking. ACL (System Demonstrations) Benjamin Heinzerling, Michael Strube
2013	—	`conf`	HITS' Monolingual and Cross-lingual Entity Linking System at TAC 2013. TAC Angela Fahrni, Benjamin Heinzerling, Thierry Göckel, Michael Strube