Papers by Jakub Binkowski

5 papers
Hallucination Detection in LLMs Using Spectral Features of Attention Maps (2025.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) have demonstrated remarkable performance across tasks but remain prone to hallucinations.
Approach: They propose a method that uses attention maps to detect hallucinations . they propose to use top-k eigenvalues of the attention maps as input to probes .
Outcome: The proposed method achieves state-of-the-art hallucination detection performance among attention-based methods.
FactSelfCheck: Fact-Level Black-Box Hallucination Detection for LLMs (2026.findings-eacl)

Copied to clipboard

Challenge: Existing methods to detect hallucinated content are limited by their tendency to generate factual errors.
Approach: They propose a black-box sampling-based method that enables fine-grained fact-level detection by representing text as interpretable knowledge graphs consisting of facts in the form of triples.
Outcome: The proposed method improves hallucination correction by 35.5% compared to baseline methods while sentence-level SelfCheckGPT yields only 10.6% improvement.
Empowering Small-Scale Knowledge Graphs: A Strategy of Leveraging General-Purpose Knowledge Graphs for Enriched Embeddings (2024.lrec-main)

Copied to clipboard

Challenge: Existing approaches to augment LLMs with Knowledge Graphs (KGs) Knowledge-intensive tasks are prone to errors and require a large amount of knowledge to be understood.
Approach: They propose a framework for augmenting LLMs through Knowledge Graphs (KGs) they propose KGs can be used to enhance performance in knowledge-intensive tasks .
Outcome: Experimental results show that a small domain-specific KG can benefit from a performance boost in downstream tasks when linked to a substantial general-purpose KG.
When Will the Tokens End? Graph-Based Forecasting for LLMs Output Length (2025.acl-srw)

Copied to clipboard

Challenge: Large Language Models (LLMs) are typically trained to predict the next token in a sequence. However, their internal representations encode signals that go beyond immediate next-token prediction.
Approach: They propose an aggregation-based model that combines hidden states from multiple transformer layers l 8, dots, 15 using element-wise operations such as mean or sum.
Outcome: The proposed model reduces NMAE by over 50% on the Alpaca dataset.
The Illusion of Progress: Re-evaluating Hallucination Detection in LLMs (2025.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) have revolutionized natural language processing, but their tendency to hallucinate poses serious challenges for reliable deployment.
Approach: They propose to use ROUGE to assess lexical overlap to determine accuracy of hallucination detection methods.
Outcome: The proposed evaluation frameworks can rival complex methods, exposing a fundamental flaw in current evaluation practices.

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