Computational Linguist; PhD Candidate @CLTLVU; Interpretability in NLP; Argument Mining
Joined April 2022
- Tweets 32
- Following 93
- Followers 69
- Likes 90
9 Photos and videos
20 Dec 2025
Do you care about metrics for model explanations?
How can human explanations guide your model?
Are explanations *sufficiently* informative?
Follow my oral pres. at IJCNLP-AACL 2025 tomorrow, or check out our paper if you're interested!
arxiv.org/abs/2511.16353
1
2
168
Jonathan Kamp retweeted
22 Jun 2024
⚠️ Citations from prompting or NLI seem plausible, but may not faithfully reflect LLM reasoning.
🏝️ MIRAGE detects context dependence in generations via model internals, producing granular and faithful RAG citations.
🚀 Demo: huggingface.co/spaces/gsarti…
Fun collab w/ @Jirui_Qi, @AriannaBisazza & @raquel_dmg! Check it out ⬇️
[1/8] Struggling with verifying the trustworthiness of RAG outputs? Check our latest work where we utilize *model internals* as a powerful and faithful tool for attributing answers to retrieved docs! (w/ @gsarti_ @AriannaBisazza @raquel_dmg)
📄: arxiv.org/abs/2406.13663
#NLProc
4
25
3,854
23 May 2024
Also at @LrecColing and interested in #interpretability in #nlp / #xai? I'm happy to tell you something about post-hoc attribution methods and their linguistic preferences 🔻
Poster session >> from 17:30 onwards
Proceedings: aclanthology.org/2024.lrec-m…
3
6
248
22 Apr 2024
Did you know that token-level differences between feature attribution methods are smoothed out if we compare them on the syntactic span level?
I'll be at @LrecColing (Turin) next month to present our paper on the linguistic preferences of such methods :) arxiv.org/abs/2403.19424
6
216
9 Dec 2023
Interested in post-hoc explanation methods? Swing by our #EMNLP2023 poster today at 10:30 to chat about their (dis)agreement and the implications of selecting the top-k most important tokens!
(arxiv.org/abs/2310.05619)
8
234
Jonathan Kamp retweeted
10 Oct 2023
Looking forward to this! We will be giving a tutorial on the current state of Transformer interpretability methods at EACL! 🇲🇹
10 Oct 2023
EACL 2024 (2/3) @eaclmeeting
- Transformer-specific Interpretability. Hosein Mohebbi, Jaap Jumelet, Michael Hanna, Afra Alishahi and Willem Zuidema.
- Item Response Theory for Natural Language Processing. João Sedoc, John P. Lalor, Pedro Rodriguez and Jose Hernandez-Orallo.
4
38
3,834
Jonathan Kamp retweeted
12 Sep 2023
Just wrapped up our presentation at #MMNLG! Big thanks to everyone for the thought-provoking questions, and kudos to @bertugatt for the seamless organisation. Can't wait to dive deeper into this work!
#SIGDIALxINLG2023
12 Sep 2023
Just watched @l__kra deliver a great presentation at the Workshop on Multimodal, Multilingual Natural Language Generation @WebNLG
#nlg #LLM #MMNLG
2
9
1,190
24 Feb 2023
What a way of visiting Groningen again after so many years: by meeting @GroNlp and presenting our research!
24 Feb 2023
Talk at @GroNlp by the invitation of @khalid_ikh with my wonderful colleagues @jb_kamp and @myrthereuver
@LIACS @hhai_conference @TMLeiden @CLTLVU @tudelft_ii
1
6
449
Jonathan Kamp retweeted
24 Feb 2023
Talk at @GroNlp by the invitation of @khalid_ikh with my wonderful colleagues @jb_kamp and @myrthereuver
@LIACS @hhai_conference @TMLeiden @CLTLVU @tudelft_ii
2
4
22
2,252
Jonathan Kamp retweeted
10 Feb 2023
Mapping Token-level Attributions to Interpretable Spans - presented by @jb_kamp
1
1
1
202
Jonathan Kamp retweeted
31 Jan 2023
Shout-out to @hmohebbi75 et al. from our #InDeep consortium for their awesome work "Quantifying Context Mixing in Transformers", introducing Value Zeroing as a new promising post-hoc interpretability approach for NLP! 🎉 Paper: arxiv.org/abs/2301.12971
ALT Benchmarking of the Value Zeroing and other methods on an example from the BLiMP dataset
1
2
12
1,330
13 Dec 2022
Some smooth work by @gsarti_ and colleagues from the #InDeep project in releasing a tool for interpreting sequence generation models. Keep up the development! @InseqDev
13 Dec 2022
After a year of restless development, I'm finally happy to announce Inseq, a new tool to democratize post-hoc interpretability of sequence generation models 🐛 github.com/inseq-team/inseq #nlproc #xai
Some highlights 👇 1/
1
2
8 Dec 2022
So far today: I've been able to virtually attend co-occurring @NllpWorkshop and #BlackboxNLP and listen to some inspiring talks. 🧙 Ito hard skills, I learned how to mute/unmute individual zoom chrome tabs
1
6
6 Dec 2022
Moonlit (moonlit.ai/) just released the interview they had with me! Check it out if you want to get some idea of what my research on #interpretability and (legal) #argmining is about! medium.com/@moonlitai.legal/…
1
5
Jonathan Kamp retweeted
5 Dec 2022
What can we learn about how named entities are represented in language models by substituting them for different ones and observing how predictions change?
Come see my poster this Thursday December 8th @ BlackboxNLP 2022 in Abu Dhabi (and online).
1
4
9
17 Oct 2022
Thanks! @khalid_ikh next time in Groningen? ;) Talking about granularity: any overlap with a paper in this same session by Mattes Ruckdeschel from @BredowInstitut? Check the proceedings here: aclanthology.org/volumes/202…
17 Oct 2022
Excellent presentation by @jb_kamp at the @argminingorg workshop 🤓 His work on cross-domain argument unit recognition investigates how model granularity relates to robustness, showing how token-based systems are more robust than sentence-based systems.
4
Jonathan Kamp retweeted
16 Oct 2022
Arrived at #ICIP2022 in Bordeaux! Check out our poster on “Humans disagree with the #IoU for measuring #objectdetector localization error”, tomorrow from 10:00 to 12:30, zone 5 😉
4
31