Papers by Irene Li

18 papers
JiraiBench: A Bilingual Benchmark for Evaluating Large Language Models’ Detection of Human risky health behavior Content in Jirai Community (2026.eacl-long)

Copied to clipboard

Challenge: a cross-lingual dataset captures a transnational cultural phenomenon . risky health behaviors (RHB) are often linked to complex mental health conditions .
Approach: They present the first cross-lingual dataset that captures a transnational cultural phenomenon . their dataset of more than 15,000 annotated social media posts forms the core of JiraiBench .
Outcome: The study shows that cultural context can be more influential than linguistic similarity . the study also shows that the Japanese prompts better handle Chinese content .
MED-COREASONER: Reducing Language Disparities in Medical Reasoning via Language-Informed Co-Reasoning (2026.acl-long)

Copied to clipboard

Challenge: Existing models that use English and local languages have a multilingual gap . a language-informed co-reasoning framework can be used to improve multilingual reasoning .
Approach: They propose a language-informed co-reasoning framework that elicits parallel English and local-language reasoning and abstracts them into structured concepts.
Outcome: Experiments show that Med-CoReasoner improves multilingual reasoning performance by 5% . the framework produces clinically sound and culturally grounded reasoning traces .
Investigating the Multilingual Calibration Effects of Language Model Instruction Tuning (2026.eacl-short)

Copied to clipboard

Challenge: despite advances in foundation model research, the relationship between large language models and their calibration remains an open area of research.
Approach: They examine a gap in the calibration of large language models within multilingual settings to better understand how data scarcity can potentially lead to different calibration effects.
Outcome: The proposed calibration gap is found in two multilingual benchmarks over 29 and 42 languages.
Better Explain Transformers by Illuminating Important Information (2024.findings-eacl)

Copied to clipboard

Challenge: Existing explanations focus on the input and output of the Transformers, resulting in confusing results.
Approach: They propose to highlight important information and eliminate irrelevant information by a refined information flow on top of the layer-wise relevance propagation method.
Outcome: The proposed method outperforms baseline models on classification and question-answering datasets with over 3% to 33% improvement on explanation metrics.
Unsupervised Cross-Domain Prerequisite Chain Learning using Variational Graph Autoencoders (2021.acl-short)

Copied to clipboard

Challenge: Existing methods to learn prerequisite relations between concepts require annotated concept pairs during training.
Approach: They propose to use an optimized variational graph autoencoder to learn prerequisite chains in unsupervised manner using an information-rich domain and an information poor domain.
Outcome: The proposed model learns to transfer concept prerequisite relations from an information-rich domain (source domain) to an information poor domain (target domain) the annotated data and resources as well as the code will be made publicly available.
SParC: Cross-Domain Semantic Parsing in Context (P19-1)

Copied to clipboard

Challenge: Xu et al., 2017): a dataset for cross-domain semantic parsing in context with 4,298 question sequences.
Approach: They present a dataset for cross-domainSemanticParsing inContext that consists of 4,298 coherent question sequences.
Outcome: The proposed dataset demonstrates that it has greater semantic diversity and can be generalized to unseen domains due to its cross-domain nature and the unseened databases at test time.
GraphCheck: Breaking Long-Term Text Barriers with Extracted Knowledge Graph-Powered Fact-Checking (2025.acl-long)

Copied to clipboard

Challenge: Existing fact-checking methods that use large language models often generate subtle factual errors.
Approach: They propose a fact-checking framework that uses extracted knowledge graphs to enhance text representation.
Outcome: GraphCheck outperforms existing specialized fact-checkers on seven benchmarks spanning general and medical domains . Graph Neural Networks process extracted knowledge graphs as a soft prompt, enabling efficient fact- checking in a single inference call.
R-VGAE: Relational-variational Graph Autoencoder for Unsupervised Prerequisite Chain Learning (2020.coling-main)

Copied to clipboard

Challenge: Concept prerequisite chain learning is an unsupervised task with no access to labeled concept pairs during training.
Approach: They propose a model that uses deep learning representations to predict concept relations . they frame concept prerequisite chain learning as an unsupervised task with no labeled concept pairs .
Outcome: The proposed model outperforms semi-supervised methods in terms of accuracy and F1 score.
Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task (D18-1)

Copied to clipboard

Challenge: Existing datasets for semantic parsing are too small in terms of number of programs for training modern data-intensive models.
Approach: They propose a large-scale complex and cross-domain semantic parsing task for a database . they use a dataset with 10,181 questions and 5,693 unique complex SQL queries .
Outcome: The proposed task is different from previous tasks because it uses the same database and program . the best model achieves only 9.7% exact matching accuracy on a database split setting.
TutorialBank: A Manually-Collected Corpus for Prerequisite Chains, Survey Extraction and Resource Recommendation (P18-1)

Copied to clipboard

Challenge: TutorialBank is a publicly available dataset that aims to facilitate NLP education and research . a google search of "Natural Language Processing" returns over 100 million hits with papers, tutorials, 1 http://aan.how blog posts, codebases and other related online resources.
Approach: They have manually collected and categorized over 5,600 resources on NLP . they have created a search engine and command-line tool to search the corpus .
Outcome: The tutorial bank dataset is the largest manually-picked corpus of resources intended for NLP education . it includes lists of research topics, relevant resources for each topic, prerequisite relations among topics .
Multi-News: A Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model (P19-1)

Copied to clipboard

Challenge: Multi-document summarization (MDS) of news articles has been limited to datasets of a couple of hundred examples.
Approach: They propose a model which integrates a traditional extractive summarization model with a standard SDS model and achieves competitive results on MDS datasets.
Outcome: The proposed model achieves competitive results on large-scale datasets.
ReAgent: Reversible Multi-Agent Reasoning for Knowledge-Enhanced Multi-Hop QA (2025.emnlp-main)

Copied to clipboard

Challenge: Multi-hop question answering (QA) is a central challenge in natural language processing . early mistakes can cause errors and undermine the final result, authors say .
Approach: They propose a reversible multi-agent reasoning framework that backtracks to earlier valid states when conflicts arise.
Outcome: Empirical evaluation shows that the framework improves on forward-only benchmarks by 6% . the approach enables agents to backtrack to valid states when conflicts arise .
MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation (2025.emnlp-main)

Copied to clipboard

Challenge: Existing large language model evaluation benchmarks focus on English, while current multilingual tasks lack parallel questions that specifically assess cross-lingual reasoning abilities.
Approach: They propose a comprehensive benchmark covering 29 languages, built on an English benchmark.
Outcome: The MMLU-ProX is a comprehensive benchmark covering 29 languages, built on an English benchmark.
HiPool: Modeling Long Documents Using Graph Neural Networks (2023.acl-short)

Copied to clipboard

Challenge: Recent work on pretraining languages have achieved satisfying results in many NLP tasks, but they are still restricted by a pre-defined maximum length.
Approach: They propose a graph-based method to model sentence-level information using a fixed length and graphs to model intra- and cross-sentence correlations.
Outcome: The proposed model outperforms baseline models by 2.6% in F1 score, and 4.8% on the longest sequence dataset.
Variational Graph Autoencoding as Cheap Supervision for AMR Coreference Resolution (2022.acl-long)

Copied to clipboard

Challenge: Abstract Meaning Representation (AMR) is a way to preserve the semantic meaning of a sentence in a graph.
Approach: They propose a general pretraining method that leverages any general AMR corpus and even automatically parses AMR data to achieve performance gains of up to 6% absolute F1 points.
Outcome: The proposed model significantly improves on the previous state-of-the-art model by up to 11% F1.
Evaluating Large Language Models on Wikipedia-Style Survey Generation (2024.findings-acl)

Copied to clipboard

Challenge: Recent studies have shown that large language models can perform well in general tasks, but their effectiveness and limitations in domainspecific tasks remain unclear.
Approach: They examine the proficiency of Large Language Models (LLMs) in generating succinct survey articles specific to the niche field of NLP in computer science.
Outcome: The LLMs perform better in generating succinct survey articles specific to the niche field of NLP in computer science, compared to human-authored surveys, but they exhibit bias in evaluation.
Leveraging Large Language Models for Learning Complex Legal Concepts through Storytelling (2024.acl-long)

Copied to clipboard

Challenge: a novel application of large language models (LLMs) to legal education helps non-experts learn complex legal concepts . authors find storytelling helps nonexperts understand complex legal terms and concepts compared to definitions .
Approach: They propose a novel application of large language models to legal education . they use LLMs to generate legal stories explaining complex legal concepts .
Outcome: The proposed method improves comprehension and interest among non-native speakers compared to definitions . the novel method also shows that non-experts retain more stories .
Surfer100: Generating Surveys From Web Resources, Wikipedia-style (2022.lrec-1)

Copied to clipboard

Challenge: Recent work on Wikipedia page generation focuses on generating the initial leading paragraph of a page, while recent pretrained language models improve upon both extractive and abstractive steps of previous models.
Approach: They propose a pretrained language model that can be combined to generate Wikipedia-style summaries with sections using 100 reference human-collected surveys.
Outcome: The proposed approach is compared with existing methods with 100 human-collected surveys.

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