Benjamin Heinzerling (@benbenhh) header
Benjamin Heinzerling (@benbenhh) profile picture

Natural Language Understanding Team Deputy Director @RIKEN_AIP, Associate Professor @TohokuNLP, based in Sendai, Japan. PhD @UniHeidelberg @HITStudies

Sendai, Japan.
Joined January 2017
Photo by Benjamin Heinzerling (@benbenhh)Photo by Benjamin Heinzerling (@benbenhh)Photo by Benjamin Heinzerling (@benbenhh)Photo by Benjamin Heinzerling (@benbenhh)Photo by Benjamin Heinzerling (@benbenhh)Photo by Benjamin Heinzerling (@benbenhh)Photo by Benjamin Heinzerling (@benbenhh)Photo by Benjamin Heinzerling (@benbenhh)Photo by Benjamin Heinzerling (@benbenhh)Photo by Benjamin Heinzerling (@benbenhh)
We've released a new version of our pretained byte pair embeddings in 275 languages. Now with pip install, automatic download of embeddings and sentencepiece models, convenient subword segmentation, and tons of pretty UMAP visualizations. nlp.h-its.org/bpemb
1
21
2
64
Benjamin Heinzerling retweeted
Thanks a lot UncertaiNLP for the spotlight 😍 The workshop was really cool, and a great ending to EMNLP
3
101
1,924
Birds of a feather on Doing NLP research in Japan @emnlpmeeting starting in 5 minutes. Join if you want to chat with people working as researchers in Japan or interested in doing so. Room is G12
2
230
Benjamin Heinzerling retweeted
Excited to share my first postdoc paper with @SheffieldNLP ! 🤩 In this work we argue that supervised uncertainty quantification (UQ) needs better evaluation Want to know more? Here's a little summary 🧵
6
9
1
93
9,741
Benjamin Heinzerling retweeted
#NLP2026 明日 3/11(水)11:15–12:45 @ B会場(B6-16)でポスター発表します! Japan ⊂ Eastern Asia ⊂ Asia ... のような概念の階層構造が,⾔語モデルの中間層にどのように・どの程度埋め込まれているかについて明らかにしました。 anlp.jp/proceedings/annual_m…
16
1
124
8,592
Benjamin Heinzerling retweeted
Benjamin Heinzerling @benbenhh さんの『人工知能』のコラム、10名の博士課程学生が一斉に雇用されるGraduiertenkolleg(Research Training Group)というドイツの仕組みを紹介していて、とても面白い。jstage.jst.go.jp/article/jjs…
2
1
752
Benjamin Heinzerling retweeted
The deadline for AACL-IJCNLP tutorial proposals is on August 14th AoE. We are interested in introductory as well as cutting edge half/full day tutorials. Introductory tutorials can be non-CL/non-NLP but interesting to the community. 2025.aaclnet.org/calls/tutor…
2
1
5
2,563
Benjamin Heinzerling retweeted
Super excited to have a cool post-doc lined up for after my PhD, working on Uncertainty Quantification with @NafiseSadat at @SheffieldNLP, and @benbenhh and @inuikentaro from RIKEN, Japan. Could not be happier 🙂
10
3
87
4,498
Benjamin Heinzerling retweeted
「言語モデルの内部機序:解析と解釈」のスライドを公開しました speakerdeck.com/eumesy/analy… 言語処理学会年次大会 #NLP2025 のチュートリアル資料です。w/ @benbenhh さん @goro_koba さん 皆で言語モデルの中を凝視していきましょう🔬
3月10日(月) に言語モデルの解釈性のチュートリアルをします🔥 @tohoku_nlp の @benbenhh さん @goro_koba さんと一緒に、モデルの内部機序(内部表象・計算メカニズム)について既存のどんな資料よりも詳しく分かりやすく解説します @ #NLP2025 長崎/オンライン。お楽しみに〜!
6
161
18
572
134,223
Benjamin Heinzerling retweeted
3月10日(月) に言語モデルの解釈性のチュートリアルをします🔥 @tohoku_nlp の @benbenhh さん @goro_koba さんと一緒に、モデルの内部機序(内部表象・計算メカニズム)について既存のどんな資料よりも詳しく分かりやすく解説します @ #NLP2025 長崎/オンライン。お楽しみに〜!
#NLP2025 では、3/10(月)午後 に、4件のチュートリアルを行います! 言語モデルの内部機序:解析と解釈(仮) Benjamin Heinzerling  先生(理化学研究所/東北大学) 横井 祥 先生(東北大学/理化学研究所) 小林 悟郎 先生(東北大学/理化学研究所) anlp.jp/nlp2025/#tutorial
2
46
3
243
89,051
Benjamin Heinzerling retweeted
🚀 Reminder! 🚀 The deadline for the Postdoc in Uncertainty Quantification for Foundation Models at @sheffieldNLP with @NafiseSadat @benbenhh @inuikentaro is March 2nd—just a few days left! 🗓️ 📆 Initial contract: 12 months (with a possibility of an additional 2-year extension)
The position is advertised for 12 months, but it has the possibility of a further 2-year extension
4
7
1,510
Benjamin Heinzerling retweeted
🚀 Postdoc Opportunity! 🚀 With @benbenhh & in collaboration with @inuikentaro, we’re hiring a Postdoc at @sheffieldNLP for Uncertainty Quantification in Foundation Models, with a chance to spend time at RIKEN, Japan! 📅 Deadline: 2 March 🔗 More info: jobs.ac.uk/job/DLS026/resear…
7
1
17
2,238
Benjamin Heinzerling retweeted
#NLP2025 では、3/10(月)午後 に、4件のチュートリアルを行います! 言語モデルの内部機序:解析と解釈(仮) Benjamin Heinzerling  先生(理化学研究所/東北大学) 横井 祥 先生(東北大学/理化学研究所) 小林 悟郎 先生(東北大学/理化学研究所) anlp.jp/nlp2025/#tutorial
16
3
51
44,898
Benjamin Heinzerling retweeted
📢 Academic Job Alert: Deadline Approaching Fast – Only 2 Days Left! (Apply by November 30th) I'm currently seeking 2 postdoctoral researchers and 3 PhD students to join my team at IT:U-Interdisciplinary Transformation University Austria (@itu_austria)!
3
16
1
47
8,107
LLMs give the right answer to questions like "When was Karl Popper born?" but do they have the right internal representation? We find evidence that they do: There are directions in activation space that have a causal, interpretable effect on the expression of numeric properties
1
4
14
2,161
By activation patching along these directions we can make the LM express earlier/smaller and larger/later values across all properties and LMs we looked at. This suggests that monotonic representation of numeric properties consistently emerges during pretraining
1
1
655
Dimension reduction via PLS reveals the monotonic structure of LM representations: There are clearly visible directions in activation space that correlate with numeric entity attributes such as birthyear, death year, and geo-coordinates
173