Papers by Seiji Maekawa
From Single to Multi: How LLMs Hallucinate in Multi-Document Summarization (2025.findings-naacl)
Copied to clipboard
| Challenge: | a recent study investigated hallucinations in multi-document summarization tasks . but, it is unclear how challenges arising from handling multiple documents affect outputs . |
| Approach: | They investigate how hallucinations manifest in large language models when summarizing topic-specific information from a set of documents. |
| Outcome: | The proposed benchmarks show that the models generate more hallucinations than baselines . the results highlight the need for more effective approaches to mitigate hallucinosity in MDS . |
Retrieval Helps or Hurts? A Deeper Dive into the Efficacy of Retrieval Augmentation to Language Models (2024.naacl-long)
Copied to clipboard
| Challenge: | Large language models (LMs) excel in retrieving popular facts, but encounter difficulty with infrequent entity-relation pairs compared to retrievers. |
| Approach: | They propose to use a WiTQA dataset to explore the effects of combinations of entities and relations on LMs. |
| Outcome: | The proposed model can retain popular relations of less common entities while retaining the same popular relations. |
Efficient Context Selection for Long-Context QA: No Tuning, No Iteration, Just Adaptive‐k (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing adaptive methods struggle with aggregation QA where optimal external context is unknown and variable. |
| Approach: | They propose a single-pass method that selects a query-specific number of passages . Adaptivek retrieval matches or outperforms fixedk baselines while using 10x fewer tokens compared to full-context input . |
| Outcome: | Adaptivek retrieval matches or outperforms fixedk baselines on factoid and aggregation QA benchmarks . it uses 10x fewer tokens than full-context input and still retrieves 70% of relevant passages compared to previous methods . |
Low-resource Interactive Active Labeling for Fine-tuning Language Models (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing active learning methods for fine-tuning language models are underperforming in low-resource, interactive labeling setting. |
| Approach: | They propose a novel active learning method that employs a hybrid sampling strategy to minimize labeling cost and acquisition latency while providing a framework for adapting to dataset diversity. |
| Outcome: | The proposed method reduces labeling cost and acquisition latency while providing a framework for adapting to dataset diversity via user guidance. |