AIConfPaper
← Search

I-Hung Hsu

20 accepted papers

2026

ATLAS: Adaptive Transfer Scaling Laws for Multilingual Pretraining, Finetuning, and Decoding the Curse of Multilinguality

Shayne Longpre, Sneha Kudugunta, Niklas Muennighoff, I-Hung Hsu, Isaac Rayburn Caswell, Alex Pentland +3
ICLR 2026poster

Scaling laws research has focused overwhelmingly on English—yet the most prominent AI models explicitly serve billions of international users. In this work, we undertake the largest multilingual scaling laws study to date, totaling 774 multilingual training experiments, spanning 10M-8B model paramet…

Cited by 0Source ↗Scholar ↗
2026

ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory

Siru Ouyang, Jun Yan, I-Hung Hsu, Yanfei Chen, Ke Jiang, Zifeng Wang +11
ICLR 2026poster

With the growing adoption of large language model (LLM) agents in persistent, real-world roles, they naturally encounter continuous streams of tasks and interactions. A key limitation, however, is their failure to learn from this accumulated experience, forcing them to discard valuable insights and…

Cited by 0Source ↗code ↗Scholar ↗
2026

Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning

Yihe Deng, I-Hung Hsu, Jun Yan, Zifeng Wang, Rujun Han, Gufeng Zhang +4
ICLR 2026poster

Large Language Models (LLMs) often struggle with challenging, multi-step reasoning problems due to a fundamental learning gap -- Reinforcement Learning with Verifiable Rewards (RLVR) suffers from sparse rewards when correct solutions are rarely sampled, while Supervised Fine-Tuning (SFT) tends to ov…

Cited by 0Source ↗Scholar ↗
2025

In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents

Zhen Tan, Jun Yan, I-Hung Hsu, Rujun Han, Zifeng Wang, Long Le +9
ACL 2025long

Large Language Models (LLMs) have made significant progress in open-ended dialogue, yet their inability to retain and retrieve relevant information from long-term interactions limits their effectiveness in applications requiring sustained personalization. External memory mechanisms have been propose…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

Magnet: Multi-turn Tool-use Data Synthesis and Distillation via Graph Translation

Fan Yin, Zifeng Wang, I-Hung Hsu, Jun Yan, Ke Jiang, Yanfei Chen +6
ACL 2025long

Large language models (LLMs) have exhibited the ability to effectively utilize external tools to address user queries. However, their performance may be limited in complex, multi-turn interactions involving users and multiple tools. To address this, we propose Magnet, a principled framework for synt…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

SNaRe: Domain-aware Data Generation for Low-Resource Event Detection

Tanmay Parekh, Yuxuan Dong, Lucas Bandarkar, Artin Kim, I-Hung Hsu, Kai-Wei Chang +1
EMNLP 2025

Event Detection (ED) – the task of identifying event mentions from natural language text – is critical for enabling reasoning in highly specialized domains such as biomedicine, law, and epidemiology. Data generation has proven to be effective in broadening its utility to wider applications without r

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2024

Argument-Aware Approach To Event Linking

I-Hung Hsu, Zihan Xue, Nilay Pochhi, Sahil Bansal, Prem Natarajan, Jayanth Srinivasa +1
ACL 2024findings

Event linking connects event mentions in text with relevant nodes in a knowledge base (KB). Prior research in event linking has mainly borrowed methods from entity linking, overlooking the distinct features of events. Compared to the extensively explored entity linking task, events have more complex…

Cited by 0Source ↗PDF ↗Scholar ↗
2024

CaLM: Contrasting Large and Small Language Models to Verify Grounded Generation

I-Hung Hsu, Zifeng Wang, Long Le, Lesly Miculicich, Nanyun Peng, Chen-Yu Lee +1
ACL 2024findings

Grounded generation aims to equip language models (LMs) with the ability to produce more credible and accountable responses by accurately citing verifiable sources. However, existing methods, by either feeding LMs with raw or preprocessed materials, remain prone to errors. To address this, we introd…

Cited by 2Source ↗PDF ↗code ↗Scholar ↗
2024

Contextual Label Projection for Cross-Lingual Structured Prediction

Tanmay Parekh, I-Hung Hsu, Kuan-Hao Huang, Kai-Wei Chang, Nanyun Peng
NAACL 2024long

Label projection, which involves obtaining translated labels and texts jointly, is essential for leveraging machine translation to facilitate cross-lingual transfer in structured prediction tasks. Prior research exploring label projection often compromise translation accuracy by favoring simplified…

Cited by 3Source ↗PDF ↗code ↗Scholar ↗
2024

TextEE: Benchmark, Reevaluation, Reflections, and Future Challenges in Event Extraction

Kuan-Hao Huang, I-Hung Hsu, Tanmay Parekh, Zhiyu Xie, Zixuan Zhang, Prem Natarajan +3
ACL 2024findings

Event extraction has gained considerable interest due to its wide-ranging applications. However, recent studies draw attention to evaluation issues, suggesting that reported scores may not accurately reflect the true performance. In this work, we identify and address evaluation challenges, including…

Cited by 14Source ↗PDF ↗code ↗Scholar ↗
2023

AMPERE: AMR-Aware Prefix for Generation-Based Event Argument Extraction Model

I-Hung Hsu, Zhiyu Xie, Kuan-Hao Huang, Prem Natarajan, Nanyun Peng
ACL 2023long

Event argument extraction (EAE) identifies event arguments and their specific roles for a given event. Recent advancement in generation-based EAE models has shown great performance and generalizability over classification-based models. However, existing generation-based EAE models mostly focus on pr…

Cited by 36Source ↗PDF ↗code ↗Scholar ↗
2023

Code-Switched Text Synthesis in Unseen Language Pairs

I-Hung Hsu, Avik Ray, Shubham Garg, Nanyun Peng, Jing Huang
ACL 2023findings

Existing efforts on text synthesis for code-switching mostly require training on code-switched texts in the target language pairs, limiting the deployment of the models to cases lacking code-switched data. In this work, we study the problem of synthesizing code-switched texts for language pairs abse…

Cited by 2Source ↗PDF ↗code ↗Scholar ↗
2023

GENEVA: Benchmarking Generalizability for Event Argument Extraction with Hundreds of Event Types and Argument Roles

Tanmay Parekh, I-Hung Hsu, Kuan-Hao Huang, Kai-Wei Chang, Nanyun Peng
ACL 2023long

Recent works in Event Argument Extraction (EAE) have focused on improving model generalizability to cater to new events and domains. However, standard benchmarking datasets like ACE and ERE cover less than 40 event types and 25 entity-centric argument roles. Limited diversity and coverage hinder the…

Cited by 24Source ↗PDF ↗code ↗Scholar ↗
2023

Multi-hop Evidence Retrieval for Cross-document Relation Extraction

Keming Lu, I-Hung Hsu, Wenxuan Zhou, Mingyu Derek Ma, Muhao Chen
ACL 2023findings

Relation Extraction (RE) has been extended to cross-document scenarios because many relations are not simply described in a single document. This inevitably brings the challenge of efficient open-space evidence retrieval to support the inference of cross-document relations,along with the challenge o…

Cited by 16Source ↗PDF ↗code ↗Scholar ↗
2023

ParaAMR: A Large-Scale Syntactically Diverse Paraphrase Dataset by AMR Back-Translation

Kuan-Hao Huang, Varun Iyer, I-Hung Hsu, Anoop Kumar, Kai-Wei Chang, Aram Galstyan
ACL 2023long

Paraphrase generation is a long-standing task in natural language processing (NLP). Supervised paraphrase generation models, which rely on human-annotated paraphrase pairs, are cost-inefficient and hard to scale up. On the other hand, automatically annotated paraphrase pairs (e.g., by machine back-t…

Cited by 14Source ↗PDF ↗code ↗Scholar ↗
2023

TAGPRIME: A Unified Framework for Relational Structure Extraction

I-Hung Hsu, Kuan-Hao Huang, Shuning Zhang, Wenxin Cheng, Prem Natarajan, Kai-Wei Chang +1
ACL 2023long

Many tasks in natural language processing require the extraction of relationship information for a given condition, such as event argument extraction, relation extraction, and task-oriented semantic parsing. Recent works usually propose sophisticated models for each task independently and pay less a…

Cited by 11Source ↗PDF ↗code ↗Scholar ↗
2022

DEGREE: A Data-Efficient Generation-Based Event Extraction Model

I-Hung Hsu, Kuan-Hao Huang, Elizabeth Boschee, Scott Miller, Prem Natarajan, Kai-Wei Chang +1
NAACL 2022long

Event extraction requires high-quality expert human annotations, which are usually expensive. Therefore, learning a data-efficient event extraction model that can be trained with only a few labeled examples has become a crucial challenge. In this paper, we focus on low-resource end-to-end event extr…

Cited by 185Source ↗PDF ↗code ↗Scholar ↗
2022

Multilingual Generative Language Models for Zero-Shot Cross-Lingual Event Argument Extraction

Kuan-Hao Huang, I-Hung Hsu, Prem Natarajan, Kai-Wei Chang, Nanyun Peng
ACL 2022long

We present a study on leveraging multilingual pre-trained generative language models for zero-shot cross-lingual event argument extraction (EAE). By formulating EAE as a language generation task, our method effectively encodes event structures and captures the dependencies between arguments. We desi…

Cited by 64Source ↗PDF ↗code ↗Scholar ↗
2022

Summarization as Indirect Supervision for Relation Extraction

Keming Lu, I-Hung Hsu, Wenxuan Zhou, Mingyu Derek Ma, Muhao Chen
EMNLP 2022finding

Relation extraction (RE) models have been challenged by their reliance on training data with expensive annotations. Considering that summarization tasks aim at acquiring concise expressions of synoptical information from the longer context, these tasks naturally align with the objective of RE, i.e.,…

Cited by 52Source ↗PDF ↗code ↗Scholar ↗
2021

ESTER: A Machine Reading Comprehension Dataset for Reasoning about Event Semantic Relations

Rujun Han, I-Hung Hsu, Jiao Sun, Julia Baylon, Qiang Ning, Dan Roth +1
EMNLP 2021main

Understanding how events are semantically related to each other is the essence of reading comprehension. Recent event-centric reading comprehension datasets focus mostly on event arguments or temporal relations. While these tasks partially evaluate machines’ ability of narrative understanding, human…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗