Papers by Jan Strich
T2-RAGBench: Text-and-Table Benchmark for Evaluating Retrieval-Augmented Generation (2026.eacl-long)
Copied to clipboard
| Challenge: | Existing QA datasets containing text-and-table data typically contain context-dependent questions, which may yield multiple correct answers depending on the provided context. |
| Approach: | They propose a benchmark to evaluate RAG methods on text-and-table data. |
| Outcome: | The proposed method evaluates RAG methods on real-world text-and-table data. |
MTabVQA: Evaluating Multi-Tabular Reasoning of Language Models in Visual Space (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing benchmarks address single tables or non-visual data, leaving a critical gap . MTabVQA comprises 3,745 complex question-answer pairs . |
| Approach: | They propose a benchmark specifically designed for multi-tabular visual question answering that measures the ability to parse diverse table images and correlate information across them. |
| Outcome: | The proposed benchmarks show that fine-tuning VLMs with MTabVQA-Instruct significantly improves their reasoning abilities. |
Comprehensive Comparison of RAG Methods Across Multi-Domain Conversational QA (2026.eacl-srw)
Copied to clipboard
| Challenge: | Existing studies evaluate RAG methods in isolation and focus on single-turn settings. |
| Approach: | They compare retrieval-augmented generation methods for multi-turn conversational QA with those that use dialogue history and coreference to ground large language models. |
| Outcome: | The proposed methods outperform vanilla RAG and advanced methods fail to yield gains and can even degrade performance below the No-RAG baseline. |
On Improving Repository-Level Code QA for Large Language Models (2024.acl-srw)
Copied to clipboard
| Challenge: | Commercial AI-assisted programming Chatbots may generate incorrect information when requests go beyond the model training data or require additional knowledge. |
| Approach: | They propose to implement different self-alignment processes and retrieval-augmented generation pipelines to improve the copilot performance. |
| Outcome: | The proposed model improves the copilot performance on repository-level semantics, dependency between files, and meta-information about the repository. |
LEMUR: A Corpus for Robust Fine-Tuning of Multilingual Law Embedding Models for Retrieval (2026.eacl-srw)
Copied to clipboard
| Challenge: | Existing large language models are not designed for semantic retrieval and PDF-based legislative sources introduce substantial noise due to imperfect text extraction. |
| Approach: | They propose a large-scale multilingual corpus of EU environmental legislation constructed from 24,953 official EUR-Lex PDF documents covering 25 languages. |
| Outcome: | The proposed model improves Top-k retrieval accuracy in monolingual and bilingual settings . it also improves accuracy in low- and high-resource languages . |