Papers by Steffen Staab

11 papers
Certainty in Uncertainty: Reasoning over Uncertain Knowledge Graphs with Statistical Guarantees (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods produce only point estimates, without quantifying predictive uncertainty—limiting their reliability in high-stakes applications where understanding confidence in predictions is crucial.
Approach: They propose a framework that generates prediction intervals guaranteed to contain the true score with a user-specified level of confidence.
Outcome: The proposed framework generates prediction intervals guaranteed to contain the true score with a user-specified level of confidence.
Knowledge Graph Embeddings using Neural Ito Process: From Multiple Walks to Stochastic Trajectories (2023.findings-acl)

Copied to clipboard

Challenge: Existing knowledge graph embeddings have problems expressing knowledge graphs because they model a specific relation r from a head h to tails by transitioning deterministically to exactly one other point in the embeddable space.
Approach: They propose a framework that models relations between nodes by relation-specific, stochastic transitions.
Outcome: The proposed framework is expressive and generic subsuming state-of-the-art models operating on low-dimensional manifolds.
Conformalized Answer Set Prediction for Knowledge Graph Embedding (2025.naacl-long)

Copied to clipboard

Challenge: Knowledge graph embeddings (KGE) map entities and predicates into numerical vectors, providing non-classical reasoning capabilities based on similarities and analogies between entities and relations.
Approach: They propose to use knowledge graph embeddings to provide non-classical reasoning capabilities by exploiting similarities and analogies between entities and relations.
Outcome: The proposed model can generate answer sets with probabilistic guarantees on four benchmark datasets and is scaled well with respect to the difficulty of the query.
What Breaks Knowledge Graph based RAG? Benchmarking and Empirical Insights into Reasoning under Incomplete Knowledge (2026.eacl-long)

Copied to clipboard

Challenge: Existing evaluation metrics and lenient answer matching criteria obscure meaningful comparisons.
Approach: They propose a general method for constructing benchmarks and a method to assess KG-RAG methods under incomplete knowledge.
Outcome: The proposed method systematically assesses KG-RAG methods under incomplete knowledge.
Is Language Modeling Enough? Evaluating Effective Embedding Combinations (2020.lrec-1)

Copied to clipboard

Challenge: specialized embeddings are not available for tasks like entity linking or paragraph classification.
Approach: They evaluate whether universal embeddings can be complemented by specialized embeddables.
Outcome: The proposed embeddings outperform state-of-the-art embeddables without any fine-tuning.
SEMMA: A Semantic Aware Knowledge Graph Foundation Model (2025.emnlp-main)

Copied to clipboard

Challenge: Existing Knowledge Graph Foundation Models (KGFMs) rely on graph structure, overlooking the rich semantic signals encoded in textual attributes.
Approach: They propose a dual-module KGFM that integrates transferable textual semantics alongside structure to generate relation identifiers.
Outcome: The proposed model outperforms ULTRA and ULtra in fully inductive link prediction in more challenging generalization settings.
Predictive Multiplicity of Knowledge Graph Embeddings in Link Prediction (2024.findings-emnlp)

Copied to clipboard

Challenge: Knowledge graph embeddings (KGE) models are often used to predict missing links for knowledge graphs (KGs) however, multiple KG embedds can give conflicting predictions for unseen queries.
Approach: They define predictive multiplicity in link prediction and introduce evaluation metrics to measure it using commonly used benchmark datasets.
Outcome: The proposed methods significantly mitigat conflicts by 66% to 78% in link prediction.
SCAIR: Schema-Conditioned Agentic Iterative Reasoning for Enterprise Knowledge Graphs (2026.acl-industry)

Copied to clipboard

Challenge: Existing agentic approaches for Knowledge Graph-based Retrieval-Augmented Generation fail to generalize to real-world enterprise Knowledge graphs (KGs) dense, schema-driven, and operationally constrained, requiring a training-free framework.
Approach: They propose a training-free framework that integrates structured planning with controlled iterative reasoning by injecting schema-conditioned structural priors and enforcing schemas during multi-hop reasoning.
Outcome: The proposed framework significantly improves on a real-world enterprise-oriented benchmark constructed from a Configuration Management DataBase (CMDB).
Predicate-Conditional Conformalized Answer Sets for Knowledge Graph Embeddings (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods provide probabilistic guarantees over a reference set of queries and answers, but they fail to identify when the answers to a query are uncertain.
Approach: They propose a method that approximates predicate-conditional coverage guarantees while maintaining compact prediction sets.
Outcome: The proposed method provides predicate-conditional coverage guarantees while maintaining compact prediction sets.
Shrinking Embeddings for Hyper-Relational Knowledge Graphs (2023.acl-long)

Copied to clipboard

Challenge: Existing studies have focused on binary relational KGs where each fact is represented by a triple.
Approach: They propose a geometric hyper-relational KG embedding method that explicitly models qualifier monotonicity, qualifier implication, and qualifier mutual exclusion.
Outcome: The proposed method outperforms existing methods on three benchmarks of hyper-relational KGs.
Disambiguating Emotional Connotations of Words Using Contextualized Word Representations (2024.starsem-1)

Copied to clipboard

Challenge: BERT, RoBERTa, XLNet, and GPT-2 models effectively discern emotional connotations of words, demonstrating superior performance and greater resilience against biases.
Approach: They propose to use contextualized word representations to examine how words can be used to distinguish emotional connotations across contexts.
Outcome: The proposed models show that they can distinguish emotional connotations of words in different contexts.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations