default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDBenjamin Heinzerling
Person information
SPARQL queries 
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
2020 – today
- 2026
[c24]Qin Dai, Benjamin Heinzerling, Kentaro Inui:
Cell-Based Representation of Relational Binding in Language Models. ACL (1) 2026: 47464-47524- [i32]Masaki Sakata, Benjamin Heinzerling, Takumi Ito, Sho Yokoi, Kentaro Inui:
Linear Representations of Hierarchical Concepts in Language Models. CoRR abs/2604.07886 (2026) - [i31]Joe Stacey, Hadas Orgad, Kentaro Inui, Benjamin Heinzerling, Nafise Sadat Moosavi:
Hidden Failures in Robustness: Why Supervised Uncertainty Quantification Needs Better Evaluation. CoRR abs/2604.11662 (2026) - [i30]Qin Dai, Benjamin Heinzerling, Kentaro Inui:
Cell-Based Representation of Relational Binding in Language Models. CoRR abs/2604.19052 (2026) - [i29]Mutsumi Sasaki, Go Kamoda, Ryosuke Takahashi, Kosuke Sato, Kentaro Inui, Keisuke Sakaguchi, Benjamin Heinzerling:
Language Models Compare Quantities Using Number-specific and Unit-specific Heuristics. CoRR abs/2606.03982 (2026) - 2025
- [c23]Masaki Sakata, Benjamin Heinzerling, Sho Yokoi, Takumi Ito, Kentaro Inui:
On Entity Identification in Language Models. ACL (Findings) 2025: 16717-16741 - [c22]Munachiso Nwadike, Zangir Iklassov, Toluwani Aremu, Tatsuya Hiraoka, Benjamin Heinzerling, Velibor Bojkovic, Hilal AlQuabeh, Martin Takác, Kentaro Inui:
Library-Like Behavior In Language Models is Enhanced by Self-Referencing Causal Cycles. ACL (1) 2025: 25365-25377 - [c21]Tatsuro Inaba, Go Kamoda, Kentaro Inui, Masaru Isonuma, Yusuke Miyao, Yohei Oseki, Yu Takagi, Benjamin Heinzerling:
How a Bilingual LM Becomes Bilingual: Tracing Internal Representations with Sparse Autoencoders. EMNLP (Findings) 2025: 13458-13470 - [c20]Mutsumi Sasaki, Go Kamoda, Ryosuke Takahashi, Kosuke Sato, Kentaro Inui, Keisuke Sakaguchi
, Benjamin Heinzerling:
Can Language Models Handle a Non-Gregorian Calendar? The Case of the Japanese wareki. IJCNLP-AACL (Short Papers) 2025: 444-463 - [c19]Ahmed Oumar El-Shangiti, Tatsuya Hiraoka, Hilal AlQuabeh, Benjamin Heinzerling, Kentaro Inui:
The Geometry of Numerical Reasoning: Language Models Compare Numeric Properties in Linear Subspaces. NAACL (Short Papers) 2025: 550-561 - [c18]Go Kamoda, Benjamin Heinzerling, Tatsuro Inaba, Keito Kudo, Keisuke Sakaguchi, Kentaro Inui:
Weight-based Analysis of Detokenization in Language Models: Understanding the First Stage of Inference Without Inference. NAACL (Findings) 2025: 6324-6343 - [i28]Munachiso Nwadike, Zangir Iklassov, Toluwani Aremu, Tatsuya Hiraoka, Velibor Bojkovic, Benjamin Heinzerling, Hilal Alqaubeh, Martin Takác, Kentaro Inui:
RECALL: Library-Like Behavior In Language Models is Enhanced by Self-Referencing Causal Cycles. CoRR abs/2501.13491 (2025) - [i27]Go Kamoda, Benjamin Heinzerling, Tatsuro Inaba, Keito Kudo, Keisuke Sakaguchi, Kentaro Inui:
Weight-based Analysis of Detokenization in Language Models: Understanding the First Stage of Inference Without Inference. CoRR abs/2501.15754 (2025) - [i26]Tatsuro Inaba, Kentaro Inui, Yusuke Miyao, Yohei Oseki, Benjamin Heinzerling, Yu Takagi:
How LLMs Learn: Tracing Internal Representations with Sparse Autoencoders. CoRR abs/2503.06394 (2025) - [i25]Ying Zhang, Benjamin Heinzerling, Dongyuan Li, Ryoma Ishigaki, Yuta Hitomi, Kentaro Inui:
Understanding Fact Recall in Language Models: Why Two-Stage Training Encourages Memorization but Mixed Training Teaches Knowledge. CoRR abs/2505.16178 (2025) - [i24]Shintaro Ozaki, Tatsuya Hiraoka, Hiroto Otake, Hiroki Ouchi, Masaru Isonuma, Benjamin Heinzerling, Kentaro Inui, Taro Watanabe, Yusuke Miyao, Yohei Oseki, Yu Takagi:
Do LLMs Need to Think in One Language? Correlation between Latent Language and Task Performance. CoRR abs/2505.21458 (2025) - [i23]Masaki Sakata, Benjamin Heinzerling, Sho Yokoi, Takumi Ito, Kentaro Inui:
On Entity Identification in Language Models. CoRR abs/2506.02701 (2025) - [i22]Ryosuke Takahashi, Tatsuro Inaba, Kentaro Inui, Benjamin Heinzerling:
TopK Language Models. CoRR abs/2506.21468 (2025) - [i21]Mutsumi Sasaki, Go Kamoda, Ryosuke Takahashi, Kosuke Sato, Kentaro Inui, Keisuke Sakaguchi, Benjamin Heinzerling:
Can Language Models Handle a Non-Gregorian Calendar? CoRR abs/2509.04432 (2025) - 2024
- [c17]Benjamin Heinzerling, Kentaro Inui:
Monotonic Representation of Numeric Attributes in Language Models. ACL (Short Papers) 2024: 175-195 - [c16]Qin Dai, Benjamin Heinzerling, Kentaro Inui:
Representational Analysis of Binding in Language Models. EMNLP 2024: 17468-17493 - [i20]Benjamin Heinzerling, Kentaro Inui:
Monotonic Representation of Numeric Properties in Language Models. CoRR abs/2403.10381 (2024) - [i19]Ana Brassard, Benjamin Heinzerling, Keito Kudo, Keisuke Sakaguchi, Kentaro Inui:
ACORN: Aspect-wise Commonsense Reasoning Explanation Evaluation. CoRR abs/2405.04818 (2024) - [i18]Ryosuke Takahashi, Go Kamoda, Benjamin Heinzerling, Keisuke Sakaguchi, Kentaro Inui:
The Curse of Popularity: Popular Entities have Catastrophic Side Effects when Deleting Knowledge from Language Models. CoRR abs/2406.06032 (2024) - [i17]Qin Dai, Benjamin Heinzerling, Kentaro Inui:
Representational Analysis of Binding in Large Language Models. CoRR abs/2409.05448 (2024) - [i16]Ahmed Oumar El-Shangiti, Tatsuya Hiraoka, Hilal AlQuabeh, Benjamin Heinzerling, Kentaro Inui:
The Geometry of Numerical Reasoning: Language Models Compare Numeric Properties in Linear Subspaces. CoRR abs/2410.13194 (2024) - 2023
- [j2]Shota Sasaki, Benjamin Heinzerling, Jun Suzuki, Kentaro Inui:
Examining the effect of whitening on static and contextualized word embeddings. Inf. Process. Manag. 60(3): 103272 (2023) - [j1]Yuta Matsumoto, Benjamin Heinzerling, Masashi Yoshikawa, Kentaro Inui:
Tracing and Manipulating Intermediate Results in Neural Math Problem Solvers. J. Nat. Lang. Process. 30(4): 1151-1171 (2023) - [c15]Haruki Nagasawa, Benjamin Heinzerling, Kazuma Kokuta, Kentaro Inui:
Can LMs Store and Retrieve 1-to-N Relational Knowledge? ACL (student) 2023: 130-138 - [c14]Pride Kavumba, Ana Brassard, Benjamin Heinzerling, Kentaro Inui:
Prompting for explanations improves Adversarial NLI. Is this true? Yes it is true because it weakens superficial cues. EACL (Findings) 2023: 2120-2135 - [c13]Go Kamoda, Benjamin Heinzerling, Keisuke Sakaguchi, Kentaro Inui:
Test-time Augmentation for Factual Probing. EMNLP (Findings) 2023: 3650-3661 - [i15]Yuta Matsumoto, Benjamin Heinzerling, Masashi Yoshikawa, Kentaro Inui:
Tracing and Manipulating Intermediate Values in Neural Math Problem Solvers. CoRR abs/2301.06758 (2023) - [i14]Go Kamoda, Benjamin Heinzerling, Keisuke Sakaguchi, Kentaro Inui:
Test-time Augmentation for Factual Probing. CoRR abs/2310.17121 (2023) - 2022
- [c12]Qin Dai, Benjamin Heinzerling, Kentaro Inui:
Cross-stitching Text and Knowledge Graph Encoders for Distantly Supervised Relation Extraction. EMNLP 2022: 6947-6958 - [c11]Ana Brassard, Benjamin Heinzerling, Pride Kavumba, Kentaro Inui:
COPA-SSE: Semi-structured Explanations for Commonsense Reasoning. LREC 2022: 3994-4000 - [i13]Ana Brassard, Benjamin Heinzerling, Pride Kavumba, Kentaro Inui:
COPA-SSE: Semi-structured Explanations for Commonsense Reasoning. CoRR abs/2201.06777 (2022) - [i12]Qin Dai, Benjamin Heinzerling, Kentaro Inui:
Cross-stitching Text and Knowledge Graph Encoders for Distantly Supervised Relation Extraction. CoRR abs/2211.01432 (2022) - 2021
- [c10]Benjamin Heinzerling, Kentaro Inui:
Language Models as Knowledge Bases: On Entity Representations, Storage Capacity, and Paraphrased Queries. EACL 2021: 1772-1791 - [c9]Pride Kavumba, Benjamin Heinzerling, Ana Brassard, Kentaro Inui:
Learning to Learn to be Right for the Right Reasons. NAACL-HLT 2021: 3890-3898 - [i11]Pride Kavumba, Benjamin Heinzerling, Ana Brassard, Kentaro Inui:
Learning to Learn to be Right for the Right Reasons. CoRR abs/2104.11514 (2021) - 2020
- [i10]Benjamin Heinzerling, Kentaro Inui:
Language Models as Knowledge Bases: On Entity Representations, Storage Capacity, and Paraphrased Queries. CoRR abs/2008.09036 (2020)
2010 – 2019
- 2019
- [b1]Benjamin Heinzerling:
Aspects of Coherence for Entity Analysis. Heidelberg University, Germany, 2019 - [c8]Benjamin Heinzerling, Michael Strube:
Sequence Tagging with Contextual and Non-Contextual Subword Representations: A Multilingual Evaluation. ACL (1) 2019: 273-291 - [c7]Yi Zhu, Benjamin Heinzerling, Ivan Vulic, Michael Strube, Roi Reichart, Anna Korhonen:
On the Importance of Subword Information for Morphological Tasks in Truly Low-Resource Languages. CoNLL 2019: 216-226 - [c6]Federico López, Benjamin Heinzerling, Michael Strube:
Fine-Grained Entity Typing in Hyperbolic Space. RepL4NLP@ACL 2019: 169-180 - [i9]Benjamin Heinzerling, Michael Strube:
Sequence Tagging with Contextual and Non-Contextual Subword Representations: A Multilingual Evaluation. CoRR abs/1906.01569 (2019) - [i8]Federico López, Benjamin Heinzerling, Michael Strube:
Fine-Grained Entity Typing in Hyperbolic Space. CoRR abs/1906.02505 (2019) - [i7]Yi Zhu, Benjamin Heinzerling, Ivan Vulic, Michael Strube, Roi Reichart, Anna Korhonen:
On the Importance of Subword Information for Morphological Tasks in Truly Low-Resource Languages. CoRR abs/1909.12375 (2019) - [i6]Paul Reisert, Benjamin Heinzerling, Naoya Inoue, Shun Kiyono, Kentaro Inui:
Riposte! A Large Corpus of Counter-Arguments. CoRR abs/1910.03246 (2019) - [i5]Pride Kavumba, Naoya Inoue, Benjamin Heinzerling, Keshav Singh, Paul Reisert, Kentaro Inui:
When Choosing Plausible Alternatives, Clever Hans can be Clever. CoRR abs/1911.00225 (2019) - 2018
- [c5]Benjamin Heinzerling, Michael Strube:
BPEmb: Tokenization-free Pre-trained Subword Embeddings in 275 Languages. LREC 2018 - [c4]Markus Zopf, Teresa Botschen, Tobias Falke, Benjamin Heinzerling, Ana Marasovic, Todor Mihaylov, Avinesh P. V. S., Eneldo Loza Mencía, Johannes Fürnkranz, Anette Frank:
What's Important in a Text? An Extensive Evaluation of Linguistic Annotations for Summarization. SNAMS 2018: 272-277 - 2017
- [c3]Benjamin Heinzerling, Michael Strube, Chin-Yew Lin:
Trust, but Verify! Better Entity Linking through Automatic Verification. EACL (1) 2017: 828-838 - [c2]Benjamin Heinzerling, Nafise Sadat Moosavi, Michael Strube:
Revisiting Selectional Preferences for Coreference Resolution. EMNLP 2017: 1332-1339 - [i4]Benjamin Heinzerling, Nafise Sadat Moosavi, Michael Strube:
Revisiting Selectional Preferences for Coreference Resolution. CoRR abs/1707.06456 (2017) - [i3]Benjamin Heinzerling, Michael Strube:
BPEmb: Tokenization-free Pre-trained Subword Embeddings in 275 Languages. CoRR abs/1710.02187 (2017) - 2015
- [c1]Benjamin Heinzerling, Michael Strube:
Visual Error Analysis for Entity Linking. ACL (System Demonstrations) 2015: 37-42 - [i2]Benjamin Heinzerling, Alex Judea, Michael Strube:
HITS at TAC KBP 2015: Entity Discovery and Linking, and Event Nugget Detection. TAC 2015 - 2013
- [i1]Angela Fahrni, Benjamin Heinzerling, Thierry Göckel, Michael Strube:
HITS' Monolingual and Cross-lingual Entity Linking System at TAC 2013. TAC 2013
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from 
to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the 
of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from 
, 
, and 
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from 
.
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2026-07-08 01:35 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated, funded, and maintained by:
Schloss Dagstuhl - Leibniz Center for Informatics is a member of the Leibniz Association and is funded by the federal government of Germany and the states of Germany, especially Saarland and Rhineland‑Palatinate.
