Operads for compositional reasoning in LLMs
Paper • 2606.13634 • Published
AI & ML interests
The research group on Language, Learning and Inference at the University of Tübingen (TüLLI-AI).
Recent Activity
View all activity
yakazimir
authored 4
papers about 2 months ago
From Token Probabilities to Semantic Constraints: Towards Declarative Probabilistic Evaluation of Language Models
Paper • 2609.13520 • Published
Operadic consistency: a label-free signal for compositional reasoning failures in LLMs
Paper • 2606.13649 • Published
ArtifactLinker: Linking Scientific Artifacts for Automatic State-of-the-Art Discovery
Paper • 2605.16902 • Published • 1
yakazimir
authored 4
papers 6 months ago
AstaBench: Rigorous Benchmarking of AI Agents with a Scientific Research Suite
Paper • 2510.21652 • Published • 4
TinyScientist: An Interactive, Extensible, and Controllable Framework for Building Research Agents
Paper • 2510.06579 • Published
Probabilistic Programs of Thought
Paper • 2604.17290 • Published
Analytica: Soft Propositional Reasoning for Robust and Scalable LLM-Driven Analysis
Paper • 2604.23072 • Published
yakazimir
authored 2
papers over 1 year ago
yakazimir
authored a
paper about 2 years ago
yakazimir
authored 2
papers over 2 years ago
yakazimir
authored 7
papers almost 3 years ago
Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research
Paper • 2402.00159 • Published • 67
OLMo: Accelerating the Science of Language Models
Paper • 2402.00838 • Published • 85
Learning Semantic Correspondences in Technical Documentation
Paper • 1705.04815 • Published
A Language for Function Signature Representations
Paper • 1804.00987 • Published
Function Assistant: A Tool for NL Querying of APIs
Paper • 1706.00468 • Published
Text Modular Networks: Learning to Decompose Tasks in the Language of Existing Models
Paper • 2009.00751 • Published
Temporal Reasoning on Implicit Events from Distant Supervision
Paper • 2010.12753 • Published