8 papers
Evaluating Federated Pre-Training: On the Reliability of Downstream Fine-Tuning and Intrinsic Evaluation
Claudia Grosser, Maike Heuer, Denis Krompass +1
Federated pre-training offers a way to train foundation models on private or distributed data without centralizing the underlying datasets. However, evaluating federated pre-traini…
Agent4cs: A Multi-agent System for Code Summarization in Large Hierarchical Codebases
Yongjian Tang, Ezgi Sarikayak, Doruk Tuncel +2
Understanding large, complex codebases, especially those with obfuscated structures and incomplete documentation, remains a significant challenge. Existing code summarization solut…
LLM-Based Agentic Systems for Software Engineering: Challenges and Opportunities
Yongjian Tang, Thomas Runkler
Despite recent advancements in Large Language Models (LLMs), complex Software Engineering (SE) tasks require more collaborative and specialized approaches. This concept paper syste…
The Few-shot Dilemma: Over-prompting Large Language Models
Yongjian Tang, Doruk Tuncel, Christian Koerner +1
Over-prompting, a phenomenon where excessive examples in prompts lead to diminished performance in Large Language Models (LLMs), challenges the conventional wisdom about in-context…
Wiki-TabNER: Integrating Named Entity Recognition into Wikipedia Tables
Aneta Koleva, Martin Ringsquandl, Ahmed Hatem +2
Interest in solving table interpretation tasks has grown over the years, yet it still relies on existing datasets that may be overly simplified. This is potentially reducing the ef…
FsPONER: Few-shot Prompt Optimization for Named Entity Recognition in Domain-specific Scenarios
Yongjian Tang, Rakebul Hasan, Thomas Runkler
Large Language Models (LLMs) have provided a new pathway for Named Entity Recognition (NER) tasks. Compared with fine-tuning, LLM-powered prompting methods avoid the need for train…