Alexander Koller @alkoller X Profile

Alexander Koller

@alkoller

Followers

1K

Following

336

Media

4

Statuses

191

Professor, musician, speaker of @neuroexplicit. This account is inactive - please find me at https://t.co/hizq2axlKP

https://t.co/UyeC2cVfQs

Joined March 2009

Don't wanna be here? Send us removal request.

Alexander Koller

@alkoller

8 months

This is a great opportunity to work with world-class faculty. The 16 PhD students who have already joined are excellent and fun. I hope to hear from you! #NLP #nlproc

Neuroexplicit Models of Language, Vision, Action

@neuroexplicit

8 months

Final opportunity: Multiple PhD students to start in Fall 2025. Combine neural and symbolic/interpretable models of language, vision, and action, and work with world-class advisors at @Saar_Uni, MPI Informatics, @mpi_sws, @CISPA ,@DFKI. Details:

0

1

3

Alexander Koller

@alkoller

9 months

Come work with me and my amazing colleagues! #nlproc #LLM

Neuroexplicit Models of Language, Vision, Action

@neuroexplicit

9 months

Now hiring: Multiple PhD students to start in fall 2025, for research on combining neural and symbolic/interpretable models of language, vision, and action. Work with world-class advisors at @Saar_Uni, MPI Informatics, @mpi_sws, @CISPA ,@DFKI. Details:

0

3

5

Alexander Koller

@alkoller

11 months

I am following my university in leaving Twitter. I would be very pleased if you chose to reconnect with me at https://t.co/A6x29Ulsxs See you there! https://t.co/fojL1RL8uT

researchprofessionalnews.com

Changes to the social media platform make further use “untenable”, group says

0

1

Alexander Koller

@alkoller

1 year

AutoPlanBench 2.0 now evaluates LLMs as planners on more than 50 domains. ReAct (with GPT-4o) is often worse, but sometimes better than symbolic planners. https://t.co/gvOSkG5yIX #nlproc

1

0

3

Alexander Koller

@alkoller

1 year

Come do research with me, my fantastic colleagues, and some of the coolest PhD students I've ever met! #NLProc #nesy #neurosymbolic #AI #ML

Neuroexplicit Models of Language, Vision, Action

@neuroexplicit

1 year

Now hiring: Twelve (!) PhD students to start in fall 2025, for research on combining neural and symbolic/interpretable models of language, vision, and action. Work with world-class advisors at @Saar_Uni, MPI Informatics, @mpi_sws, @CISPA, @DFKI. Details:

1

2

10

antonio vergari ⚔️ not at #ICML2025

@tetraduzione

1 year

spending a great week in Saarland for the @neuroexplicit retreat of @SIC_Saar. great talks, posters and interactions with #PhD students on #neurosymbolic #nesy #AI #ML (and boardgames!) Thanks @alkoller @slusallek @IValeraM for having me!

0

3

19

Alexander Koller

@alkoller

1 year

So proud of my postdoc Mareike Hartmann for this excellent work.

ACL 2026

@aclmeeting

1 year

🏆 ACL Best Resource Paper Award: AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents by Trivedi et al. #NLProc #ACL2024NLP

1

17

Alexander Koller

@alkoller

1 year

It was fun to apply #NLProc methods to software engineering with my brilliant colleague @AndreasZeller and his student @TurikMammadov. The coolest part, to me, is that you can backtranslate program outputs into program inputs. Let's see where this will go!

Andreas Zeller

@AndreasZeller

1 year

Learning models from programs! Given a program P, our MODELIZER learns a model M that mocks P's behavior, producing P's output for a given input. But M is also reversible, predicting inputs for which P produces a given output, with up to 95.4% accuracy: https://t.co/5YKbUkccpD 🧵

0

1

6

Alexander Koller

@alkoller

1 year

Can you use LLMs to replace crowdworkers in NLP evaluations? My amazing collaborators and I analyzed this broadly. Answer: Sometimes LLMs correlate very well with human judgments, but you can't rely on it.

Alberto Testoni

@alberto_testoni

1 year

1/5 📣 Excited to share “LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks”! https://t.co/BIqZCmToz1 🚀 We introduce JUDGE-BENCH, a benchmark to investigate to what extent LLM-generated judgements align with human evaluations. #NLProc

1

5

30

Alexander Koller

@alkoller

1 year

Ellie is fantastic, and I am so delighted to have her here.

Neuroexplicit Models of Language, Vision, Action

@neuroexplicit

1 year

Ellie Pavlick @Brown_NLP is visiting us for three months as a @dfg_public Mercator Fellow. We are thrilled to have her with us and look forward to many fruitful research collaborations.

0

3

@emilymbender.bsky.social

@emilymbender

2 years

This is a decent summary of the octopus thought experiment from Bender & @alkoller 2020, with two glaring exceptions, right at the start: https://t.co/zvj3w26jVr >>

techcrunch.com

What is AI? We've put together this non-technical guide to give anyone a fighting chance to understand how and why today's AI works.

2

21

85

Alexander Koller

@alkoller

2 years

Come work with my amazing colleagues and me on neurosymbolic models for #NLProc and related fields! You'll join our really excellent first nine PhD students and one of the largest research centers for neurosymbolic models in the world. @LstSaar @SIC_Saar

Neuroexplicit Models of Language, Vision, Action

@neuroexplicit

2 years

Now hiring: Three PhD students and one postdoc, as part of a research team of ~30, combining neural and symbolic/interpretable models of language, vision, action, and ML. Work with advisors at @Saar_Uni, MPI Informatics, @mpi_sws_, @CISPA, @DFKI. Details:

0

7

12

Alexander Koller

@alkoller

2 years

ChatGPT getting information from Bild - what could possibly go wrong?

OpenAI

@OpenAI

2 years

We have formed a new global partnership with @AxelSpringer and its news products. Real-time information from @politico, @BusinessInsider, European properties @BILD and @welt, and other publications will soon be available to ChatGPT users. ChatGPT’s answers to user queries will

0

5

Alexander Koller

@alkoller

2 years

Come work with my amazing colleagues and me on neurosymbolic models! You'll join our really excellent first six PhD students and one of the largest research centers for neurosymbolic models in the world. #NLProc @LstSaar @SIC_Saar

Neuroexplicit Models of Language, Vision, Action

@neuroexplicit

2 years

Now hiring: Six PhD students and one postdoc, for research on combining neural and symbolic/interpretable models of language, vision, and action and ML. Work with world-class advisors at @Saar_Uni, MPI Informatics, @mpi_sws_, @CISPA, @DFKI. Details:

0

1

6

Alexander Koller

@alkoller

2 years

Can LLMs do planning? My PhD student @Stein1Katharina built AutoPlanBench, which can automatically convert any PDDL benchmark domain into a benchmark for LLM planners, and they are not doing so hot. https://t.co/gvOSkG50Tp #NLProc

1

7

Alexander Koller

@alkoller

2 years

My student @yuekun_yao did something really cool: Predict accuracy of a seq2seq model on test data from only the inputs. Core is a discriminator that learns to check whether the model's prediction is correct. Excellent accuracy across datasets. https://t.co/MgiEvqaNWr #NLProc

1

2

11

Alexander Koller

@alkoller

2 years

A very fun piece of work that I got to collaborate on at @allen_ai: Hierarchical plans improve LLM planning on domains that have hierarchical structure.

Archiki Prasad ✈️ NeurIPS 2025

@ArchikiPrasad

2 years

How can LLM-agents dynamically adapt to task complexity & LLM capabilities "as-needed"? 🚨Introducing ADaPT to recursively intervene/decompose if task is too complex -> yields substantial gains on interactive tasks https://t.co/7f3zag1z29 w/ @ai2_aristo @allen_ai @uncnlp 🧵⬇️

1

8

Matthew Finlayson

@mattf1n

2 years

Nucleus and top-k sampling are ubiquitous, but why do they work? @johnhewtt, @alkoller, @swabhz, @Ashish_S_AI and I explain the theory and give a new method to address model errors at their source (the softmax bottleneck)! 📄 https://t.co/0zRu3x9mVg 🧑‍💻 https://t.co/A57bEb4aqb

3

26

162

Alexander Koller

@alkoller

2 years

Come work with me: Three-year postdoc position, very suitable for developing your own research agenda and collaborations. Let's figure out reliable reasoning with LLMs and personalization of text and dialogue. Neurosymbolic models welcome.

0

18

44

Alexander Koller

@alkoller

2 years

Come work with us on neurosymbolic models of #NLProc! The first three students are amazing - be part of a wonderful team that investigates the design principles of combining neural and symbolic models. #ACL2023 #ACL2023NLP

Neuroexplicit Models of Language, Vision, Action

@neuroexplicit

2 years

Now hiring: Three more PhD students and one postdoc for research on combining neural and symbolic/interpretable models of language, vision, and action. Work with world-class advisors at @Saar_Uni, MPI Informatics, @mpi_sws, @CISPA, @DFKI. Details:

0

4

11