Papers by Hangfeng He

QANom: Question-Answer driven SRL for Nominalizations (2020.coling-main)

Copied to clipboard

Ayal Klein, Jonathan Mamou, Valentina Pyatkin, Daniela Stepanov, Hangfeng He, Dan Roth, Luke Zettlemoyer, Ido Dagan

Challenge:	Traditionally, SRL annotations focus on verbal predicates, but other types of predicate are frequent in natural language.
Approach:	They propose a semantic scheme for capturing predicate-argument relations for nominalizations, termed QANom, using crowdsourcing and QA-driven annotations.
Outcome:	The proposed scheme outperforms existing annotations and is useful for downstream tasks.

Unveiling Divergent Inductive Biases of LLMs on Temporal Data (2024.naacl-short)

Copied to clipboard

Sindhu Kishore, Hangfeng He

Language Models

Challenge:	Temporal relations play a crucial role across diverse applications, including event summarization, predicting future events and medical information processing.
Approach:	They evaluate the performance of large language models in the analysis of temporal data using two prompt types, Question Answering and Textual Entailment.
Outcome:	The proposed models show that they are biased towards specific temporal relationships, while GPT-3.5 prefers “AFTER” for implicit and explicit events, while TE models lean towards “BEFORE”.

The Role of Model Confidence on Bias Effects in Measured Uncertainties for Vision-Language Models (2025.findings-emnlp)

Copied to clipboard

Xinyi Liu, Weiguang Wang, Hangfeng He

Language Models

Challenge:	Quantifying epistemic uncertainty in open-ended tasks is challenging due to the presence of aleatoric uncertainty, which arises from multiple valid answers.
Approach:	They conduct experiments on visual question answering tasks and find that mitigating prompt-introduced bias improves uncertainty quantification.
Outcome:	The proposed approach reduces uncertainty quantification in visual question answering tasks by mitigating prompt-introduced biases.

QuASE: Question-Answer Driven Sentence Encoding (2020.acl-main)

Copied to clipboard

Hangfeng He, Qiang Ning, Dan Roth

Question Answering

Challenge:	Question-answering (QA) data often encodes essential information in many facets . a growing interest of QA has led to many large-scale QA datasets available to the community .
Approach:	They propose a question-answer driven sentence encoding framework to learn representations from QA data.
Outcome:	The proposed framework learns representations from QA data, using BERT or other state-of-the-art contextual language models.

Understanding Spatial Relations through Multiple Modalities (2020.lrec-1)

Copied to clipboard

Soham Dan, Hangfeng He, Dan Roth

Visual Data in NLP

Challenge:	Existing work on common sense reasoning and understanding of spatial relations is limited.
Approach:	They propose a spatial model that uses both textual and visual information to predict spatial relations between two entities in an image.
Outcome:	The proposed model improves prediction accuracy and coverage and deals with unseen subjects, objects and relations.

Partial Or Complete, That’s The Question (N19-1)

Copied to clipboard

Qiang Ning, Hangfeng He, Chuchu Fan, Dan Roth

Multimodality

Challenge:	Existing annotation schemes aim at acquiring completely annotated structures, but partial annotations can be costly and hinder learning.
Approach:	They propose a method to find out that learning from partial structures can sometimes outperform learning from complete ones.
Outcome:	The proposed method outperforms existing methods in three different structured learning tasks.

Mitigating Hallucinations in Multimodal Spatial Relations through Constraint-Aware Prompting (2025.findings-naacl)

Copied to clipboard

Jiarui Wu, Zhuo Liu, Hangfeng He

Responsible & Trustworthy NLP

Challenge:	Existing research has explored methods to enhance the performance of large vision-language models in spatial relations.
Approach:	They propose a constraint-aware prompting framework to reduce spatial relation hallucinations by incorporating two types of constraints into the prompt.
Outcome:	The proposed framework improves on three widely-used spatial relation datasets.

An Empirical Analysis on Large Language Models in Debate Evaluation (2024.acl-short)

Copied to clipboard

Xinyi Liu, Pinxin Liu, Hangfeng He

Semantic Text Processing

Challenge:	Prior research in automatic debate evaluation relied on pre-trained encoders and the modeling of argument relations and structures.
Approach:	They investigate the capabilities and inherent biases of advanced large language models (LLMs) such as GPT-3.5 and GPT-4 in the context of debate evaluation.
Outcome:	The proposed models outperform state-of-the-art methods on extensive datasets and show that they are more accurate than previous models.

Ranking Human and LLM Texts Using Locality Statistics (2026.findings-eacl)

Copied to clipboard

Yiyang Wang, Chen Ding, Hangfeng He

Text Generation

Challenge:	The paper extends the Data Movement Distance (DMD) metric defined to measure the locality in computer memory to text by defining a new term designed to better characterize low-frequency tokens.
Approach:	They propose to define a normalized version of the Data Movement Distance (nDMD) term is designed to better characterize low-frequency tokens.
Outcome:	The proposed normalized version outperforms baselines and improves performance on the English subset of the M4 dataset and the GenAI detection shared task.

SocREval: Large Language Models with the Socratic Method for Reference-free Reasoning Evaluation (2024.findings-naacl)

Copied to clipboard

Hangfeng He, Hongming Zhang, Dan Roth

Language Models

Challenge:	Existing reference-free reasoning evaluation metrics rely on human-annotated reasoning chains as references, but require fine-tuning with human-derived chains before evaluation.
Approach:	They propose to use GPT-4 to automatically evaluate reasoning chain quality by leveraging the Socratic method.
Outcome:	Empirical results show that the proposed approach significantly improves existing reference-free reasoning evaluation metrics.

On the Role of Model Prior in Real-World Inductive Reasoning (2025.emnlp-main)

Copied to clipboard

Zhuo Liu, Ding Yu, Hangfeng He

Reasoning

Challenge:	Existing studies have evaluated the inductive reasoning capabilities of Large Language Models (LLMs) by evaluating their ability to generate textual hypotheses based on in-context input-output pairs and test these hypothese based upon unseen examples.
Approach:	They evaluated three inductive reasoning strategies across five real-world tasks with three LLMs and found that hypothesis generation is primarily driven by the model’s inherent priors.
Outcome:	The proposed models generate high-quality hypotheses that can generalize to new instances when guided by in-context demonstrations.

TreeRare: Syntax Tree-Guided Retrieval and Reasoning for Knowledge-Intensive Question Answering (2025.emnlp-main)

Copied to clipboard

Boyi Zhang, Zhuo Liu, Hangfeng He

Question Answering

Challenge:	Existing work shows that large language models generate incorrect statements due to over-reliance on parametric knowledge.
Approach:	They propose a framework that utilizes syntax trees to guide information retrieval and reasoning for question answering.
Outcome:	The proposed framework improves on existing state-of-the-art methods for large-scale query processing.

Same Company, Same Signal: The Role of Identity in Earnings Call Transcripts (2025.findings-acl)

Copied to clipboard

Ding Yu, Zhuo Liu, Hangfeng He

Challenge:	Existing studies rely on earnings call transcripts to predict volatility, but current models focus on capturing ticker identity rather than providing meaningful insights specific to each earnings.
Approach:	They propose a dataset that provides 20 earnings records per ticker to help predict volatility . they propose two training-free baselines to capture ticker-specific patterns .
Outcome:	The proposed dataset provides 20 earnings records per ticker, with a priorAfterMarket attribute and dense ticker coverage.

Foreseeing the Benefits of Incidental Supervision (2021.emnlp-main)

Copied to clipboard

Hangfeng He, Mingyuan Zhang, Qiang Ning, Dan Roth

Challenge:	Real-world applications often require improved models by leveraging a range of cheap incidental supervision signals.
Approach:	They propose a unified PAC-Bayesian motivated informativeness measure that characterizes the uncertainty reduction provided by incidental supervision signals.
Outcome:	The proposed measure quantifies the value added by incidental supervision signals to sequence tagging tasks.

Analyzing Uncertainty of LLM-as-a-Judge: Interval Evaluations with Conformal Prediction (2025.emnlp-main)

Copied to clipboard

Huanxin Sheng, Xinyi Liu, Hangfeng He, Jieyu Zhao, Jian Kang

Challenge:	Large language models (LLMs) are powerful automatic evaluators for natural language generation (NLG) tasks, but their uncertainty may limit their deployment in many applications.
Approach:	They propose a conformal prediction framework that provides a prediction interval with coverage guarantees and a midpoint-based score as a low-bias alternative to raw model score and weighted average.
Outcome:	The proposed framework provides a prediction interval with coverage guarantees and a midpoint-based score as a low-bias alternative to raw model score and weighted average.