Papers by Hayate Iso

10 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.
XATU: A Fine-grained Instruction-based Benchmark for Explainable Text Updates (2024.lrec-main)

Copied to clipboard

Challenge: Existing text editing benchmark datasets contain coarse-grained instructions and lack explainability, resulting in outputs that deviate from intended changes.
Approach: They propose a benchmark specifically designed for fine-grained instruction-based explainable text editing.
Outcome: The proposed benchmark incorporates fine-grained instructions and gold-standard edit explanations.
Learning to Select, Track, and Generate for Data-to-Text (P19-1)

Copied to clipboard

Challenge: Existing models often refer to the same data record multiple times.
Approach: They propose a data-to-text generation model with two modules, one for tracking and the other for text generation.
Outcome: The proposed model outperforms existing models even without writer information in all evaluation metrics and contributes to content planning and surface realization.
AmbigNLG: Addressing Task Ambiguity in Instruction for NLG (2024.emnlp-main)

Copied to clipboard

Challenge: AmbigNLG is a novel task designed to tackle task ambiguity in instructions for NLG . ambiguous instructions often impede the performance of Large Language Models (LLMs) .
Approach: They propose an ambiguity taxonomy that categorizes different types of instruction ambiguities and refines initial instructions with clearer specifications.
Outcome: The proposed task improves alignment of generated text with user expectations, achieving 15.02-point increase in ROUGE scores.
Convex Aggregation for Opinion Summarization (2021.findings-emnlp)

Copied to clipboard

Challenge: Recent advances in text autoencoders have significantly improved the quality of the latent space, allowing models to generate consistent text from aggregated latent vectors.
Approach: They develop a framework which searches input-output word overlap for latent vector aggregation.
Outcome: The proposed framework improves the quality of the latent space and establishes state-of-the-art performance on two opinion summarization benchmarks.
Less is More for Long Document Summary Evaluation by LLMs (2024.eacl-short)

Copied to clipboard

Challenge: Large Language Models (LLMs) have shown promising performance in summary evaluation tasks, yet they face challenges such as high computational cost and the Lost-in-the-middle problem where important information in the middle of long documents is often overlooked.
Approach: They propose a novel method which extracts key sentences from a long source document and then evaluates the summary by prompting LLMs.
Outcome: The proposed method significantly reduces evaluation costs and exhibits a higher correlation with human evaluations.
Fact-based Text Editing (2020.acl-main)

Copied to clipboard

Challenge: Existing methods for fact-based text editing are not suitable for all situations.
Approach: They propose a method for automatically generating a dataset with a draft text, revised text, and several facts represented in triples.
Outcome: The proposed method outperforms the encoder-decoder approach on two datasets and shows that it conducts inference faster than the encoded-decoding approach.
Evaluating Bias in LLMs for Job-Resume Matching: Gender, Race, and Education (2025.naacl-industry)

Copied to clipboard

Challenge: Large Language Models (LLMs) have potential to automate hiring but inherent biases may lead to unfair hiring practices.
Approach: They evaluate how factors such as gender, race, and educational background influence model decisions.
Outcome: The proposed model reduces biases related to gender and race, but implicit biase concerning educational background remains significant.
Comparative Opinion Summarization via Collaborative Decoding (2022.findings-acl)

Copied to clipboard

Challenge: Existing opinion summarization methods are insufficient to help users compare multiple choices.
Approach: They propose a comparative opinion summarization task that generates two contrastive summaries and one common summary from two different candidate sets of reviews.
Outcome: The proposed framework produces higher-quality contrastive and common summaries than state-of-the-art models.

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