Papers by Seiji Maekawa

4 papers
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.

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