Papers by Lifu Huang

From Passive Metric to Active Signal: The Evolving Role of Uncertainty Quantification in Large Language Models (2026.findings-acl)

Challenge:	Recent pre-trained language models have produced impressive results, but there is still a gap between human written texts and machine-generated outputs.
Approach:	They propose a multi-task training strategy for long text generation grounded on the cognitive theory of writing.
Outcome:	The proposed model achieves better results on three open-ended generation tasks than baselines.

Copied to clipboard

Jiaxin Zhang, Wendi Cui, Zhuohang Li, Lifu Huang, Bradley A. Malin, Caiming Xiong, Chien-Sheng Wu

The Future is not One-dimensional: Complex Event Schema Induction by Graph Modeling for Event Prediction (2021.emnlp-main)

Challenge:	Large Language Models (LLMs) have remarkable capabilities, but unreliability remains a barrier to deployment in high-stakes domains.
Approach:	They propose to transform uncertainty from a passive diagnostic metric to an active control signal guiding real-time model behavior.
Outcome:	The proposed model evolution from passive diagnostic metric to active control signal is critical for high-stakes applications.

Copied to clipboard

Manling Li, Sha Li, Zhenhailong Wang, Lifu Huang, Kyunghyun Cho, Heng Ji, Jiawei Han, Clare Voss

Structured Data in NLP

Challenge:	Event schemas encode knowledge of stereotypical structures of events and their connections . previous work on event schema induction focuses on atomic events or linear temporal sequences .
Approach:	They propose a Temporal Complex Event Schema: a graph-based schema representation that encompasses events, arguments, temporal connections and argument relations.
Outcome:	The proposed model outperforms existing models on HITS@1 by 17.8%.

Entity-aware Image Caption Generation (D18-1)

Copied to clipboard

Di Lu, Spencer Whitehead, Lifu Huang, Heng Ji, Shih-Fu Chang

LLM Braces: Straightening Out LLM Predictions with Relevant Sub-Updates (2025.acl-long)

Challenge:	Existing image captioning approaches generate generic descriptions of visual content and ignore background information.
Approach:	They propose a task which generates informative image captions using images and hashtags as input.
Outcome:	The proposed model outperforms unimodal baselines significantly with evaluation metrics on a dataset from Flickr.

Copied to clipboard

Ying Shen, Lifu Huang

Teamwork Is Not Always Good: An Empirical Study of Classifier Drift in Class-incremental Information Extraction (2023.findings-acl)

Challenge:	Recent studies reveal that much of the knowledge in a Transformer-based Large Language Model (LLM) is encoded in its feed-forward (FFN) layers, where each FNN layer can be interpreted as the summation of sub-updates, each corresponding to a weighted column vector from the FFN’s value parameter matrix.
Approach:	They propose a method that computes relevance scores associated with value vectors in FFN layers and leverages these scores to dynamically adjust the contribution of sub-updates.
Outcome:	The proposed framework outperforms baseline approaches in fine-tuning and zero-shot settings while requiring significantly fewer tunable parameters.

Copied to clipboard

Minqian Liu, Lifu Huang

Ameli: Enhancing Multimodal Entity Linking with Fine-Grained Attributes (2024.eacl-long)

Challenge:	Existing methods for learning incrementally do not address the problem of class-incremental learning.
Approach:	They propose a framework that can continuously learn new classes from a data stream without forgetting previously learned classes.
Outcome:	The proposed framework shows significant improvement over the state-of-the-art frameworks with up to 44.7% absolute F-score gain.

Copied to clipboard

Barry Yao, Sijia Wang, Yu Chen, Qifan Wang, Minqian Liu, Zhiyang Xu, Licheng Yu, Lifu Huang

Learning from a Friend: Improving Event Extraction via Self-Training with Feedback from Abstract Meaning Representation (2023.findings-acl)

Challenge:	Experimental results show that understanding attributes of mentions from text descriptions and visual images plays a vital role in multimodal entity linking.
Approach:	They propose to integrate attributes into multimodal entity linking using a text-image-based knowledge base.
Outcome:	The proposed approach integrates attributes into disambiguation.

Copied to clipboard

Zhiyang Xu, Jay Yoon Lee, Lifu Huang

Query and Extract: Refining Event Extraction as Type-oriented Binary Decoding (2022.findings-acl)

Challenge:	Existing data scarcity hinders the progress of event extraction, authors say . ACE-052 has 10 of the 33 event types with less than 80 annotations, authors claim .
Approach:	They propose a self-training with feedback framework that leverages large-scale unlabeled data to acquire feedback for each new event prediction from the unlabed data.
Outcome:	The proposed framework improves event extraction models even when unlabeled data are unavailable.

Copied to clipboard

Sijia Wang, Mo Yu, Shiyu Chang, Lichao Sun, Lifu Huang

Extracting Temporal Event Relation with Syntax-guided Graph Transformer (2022.findings-naacl)

Challenge:	Existing approaches to event extraction are limited to a set of pre-defined types.
Approach:	They propose a natural language query framework that uses event types and argument roles to extract candidate triggers and arguments from input text.
Outcome:	The proposed framework outperforms existing methods on zero-shot event extraction.

Copied to clipboard

Shuaicheng Zhang, Qiang Ning, Lifu Huang

Incremental Prompting: Episodic Memory Prompt for Lifelong Event Detection (2022.coling-1)

Challenge:	Temporal relationship extraction is crucial for understanding complex events and reasoning over them.
Approach:	They propose a Syntax-guided Graph Transformer network to extract temporal relations between events by explicitly exploiting the connection between two events based on their dependency parsing trees.
Outcome:	The proposed approach outperforms state-of-the-art methods on MATRES and TB-DENSE with up to 7.9% absolute F-score gain.

Copied to clipboard

Minqian Liu, Shiyu Chang, Lifu Huang

MEPT: Mixture of Expert Prompt Tuning as a Manifold Mapper (2025.emnlp-main)

Challenge:	Existing methods to improve lifelong event detection performance are limited by the limited stored examples.
Approach:	They propose to use Episodic Memory Prompts to explicitly retain the learned task-specific knowledge.
Outcome:	The proposed method can be used to update a model with new event types while retaining the capability on previously learned types.

Copied to clipboard

Runjia Zeng, Guangyan Sun, Qifan Wang, Tong Geng, Sohail Dianat, Xiaotian Han, Raghuveer Rao, Xueling Zhang, Cheng Han, Lifu Huang, Dongfang Liu

M2PT: Multimodal Prompt Tuning for Zero-shot Instruction Learning (2024.emnlp-main)

Challenge:	Empirical evaluations show that Mixture of Expert Prompt Tuning outperforms state-of-the-art parameter efficient baselines on SuperGLUE.
Approach:	They propose a pretrain-then-fine-tune paradigm for manifold mapping using multiple prompt experts.
Outcome:	Empirical results show that the proposed approach outperforms state-of-the-art methods on SuperGLUE while reducing activated prompts by 79.25%.

Copied to clipboard

Taowen Wang, Yiyang Liu, James Liang, Junhan Zhao, Yiming Cui, Yuning Mao, Shaoliang Nie, Jiahao Liu, Fuli Feng, Zenglin Xu, Cheng Han, Lifu Huang, Qifan Wang, Dongfang Liu

The Art of SOCRATIC QUESTIONING: Recursive Thinking with Large Language Models (2023.emnlp-main)

Challenge:	Multimodal Large Language Models (MLLMs) exhibit remarkable performance across a wide range of domains.
Approach:	They propose a multimodal prompt tuning approach for efficient instruction tuning of MLLMs.
Outcome:	The proposed approach shows superior performance on multimodal evaluation datasets compared to state-of-the-art methods.

Copied to clipboard

Jingyuan Qi, Zhiyang Xu, Ying Shen, Minqian Liu, Di Jin, Qifan Wang, Lifu Huang

Semi-supervised New Event Type Induction and Event Detection (2020.emnlp-main)

Challenge:	Chain-of-Thought (CoT) prompting relies on the initial decisions, causing errors in early steps to accumulate and impact the final answers.
Approach:	They propose a divide-and-conquer style algorithm that leverages large language models to raise and answer sub-questions until collecting enough information to tackle the original one.
Outcome:	The proposed algorithm is more robust to errors and errors than CoT prompting and Tree-of-Thought prompting methods.

Copied to clipboard

Lifu Huang, Heng Ji

The Art of Prompting: Event Detection based on Type Specific Prompts (2023.acl-short)

Challenge:	Existing event extraction studies assume a set of event types and corresponding annotations are given, which could be expensive.
Approach:	They propose a semi-supervised task of event type induction to learn seen and unseen types . they use seen type annotations to optimize the process and enforce the reconstruction .
Outcome:	The proposed method achieves state-of-the-art on supervised event detection and discovers high-quality new types.

Copied to clipboard

Sijia Wang, Mo Yu, Lifu Huang

Low-Resource NLP

Challenge:	Experimental results show that a well-defined and comprehensive description of event types can significantly improve event detection performance when the annotations are limited.
Approach:	They propose a unified framework to integrate event type specific prompts for supervised, few-shot and zero-shot event detection.
Outcome:	The proposed framework shows up to 22.2% gain over the prior state-of-the-art frameworks.

Paper Abstract Writing through Editing Mechanism (P18-2)

Copied to clipboard

Qingyun Wang, Zhihao Zhou, Lifu Huang, Spencer Whitehead, Boliang Zhang, Heng Ji, Kevin Knight

Challenge:	a paper abstract writing system can automatically generate an abstract from a title . a typical recurrent neural network (RNN) based approach easily loses focus.
Approach:	They propose a paper abstract writing system that automatically generates an abstract from a title.
Outcome:	The proposed system passes Turing tests by junior domain experts and non-experts at a rate up to 80%.

How Knowledge Graph and Attention Help? A Qualitative Analysis into Bag-level Relation Extraction (2021.acl-long)

Copied to clipboard

Zikun Hu, Yixin Cao, Lifu Huang, Tat-Seng Chua

Knowledge Representation

Challenge:	Knowledge Graph (KG) and attention mechanism have been demonstrated effective in introducing and selecting useful information for weakly supervised methods.
Approach:	They propose a paradigm to quantitatively evaluate the effect of attention and KG on bag-level relation extraction (RE) they propose to incorporate entity prior to KG-enhanced attention to improve RE performance .
Outcome:	The proposed model achieves significant improvements on two real-world datasets compared with three state-of-the-art baselines.

X-Eval: Generalizable Multi-aspect Text Evaluation via Augmented Instruction Tuning with Auxiliary Evaluation Aspects (2024.naacl-long)

Copied to clipboard

Minqian Liu, Ying Shen, Zhiyang Xu, Yixin Cao, Eunah Cho, Vaibhav Kumar, Reza Ghanadan, Lifu Huang

Text Generation

Challenge:	X-Eval is a two-stage instruction tuning framework to evaluate text in both seen and unseen aspects customized by end users.
Approach:	They introduce a two-stage instruction tuning framework to evaluate text in both seen and unseen aspects customized by end users.
Outcome:	The proposed framework improves the model’s ability to follow evaluation instructions and enhances the learning stage to better assess text quality.

PLANET: Dynamic Content Planning in Autoregressive Transformers for Long-form Text Generation (2022.acl-long)

Copied to clipboard

Zhe Hu, Hou Pong Chan, Jiachen Liu, Xinyan Xiao, Hua Wu, Lifu Huang

InternalInspector I2: Robust Confidence Estimation in LLMs through Internal States (2024.findings-emnlp)

Challenge:	Existing methods for text generation still suffer from incoherence problems . Neural sequence-to-sequence (seq2sequ) models generate fluent results .
Approach:	They propose a novel generation framework that leverages autoregressive self-attention mechanism to conduct content planning and surface realization dynamically.
Outcome:	The proposed framework outperforms baseline models and generates more coherent texts with richer contents.

Copied to clipboard

Mohammad Beigi, Ying Shen, Runing Yang, Zihao Lin, Qifan Wang, Ankith Mohan, Jianfeng He, Ming Jin, Chang-Tien Lu, Lifu Huang

Cross-lingual Multi-Level Adversarial Transfer to Enhance Low-Resource Name Tagging (N19-1)

Challenge:	Large Language Models (LLMs) often struggle with generating reliable outputs, often producing high-confidence inaccuracies known as hallucinations.
Approach:	They propose a framework that leverages contrastive learning on internal states including attention states, feed-forward states, and activation states of all layers to enhance confidence estimation in LLMs.
Outcome:	The framework outperforms existing methods in the hallucination detection benchmark HaluEval and the previous methods at the same time.

Copied to clipboard

Lifu Huang, Heng Ji, Jonathan May

X-Shot: A Unified System to Handle Frequent, Few-shot and Zero-shot Learning Simultaneously in Classification (2024.findings-acl)

Challenge:	Low-resource language name tagging is an important but challenging task.
Approach:	They propose a neural architecture that leverages multi-level adversarial transfer to improve name tagging for low-resource languages.
Outcome:	The proposed approach outperforms previous approaches on CoNLL data sets.

Copied to clipboard

Hanzi Xu, Muhao Chen, Lifu Huang, Slobodan Vucetic, Wenpeng Yin

UniHGKR: Unified Instruction-aware Heterogeneous Knowledge Retrievers (2025.naacl-long)

Challenge:	Recent studies have focused on few-shot and zero-shot learning, but label occurrences vary widely . authors propose a new classification challenge that can be used to manage labels across the full frequency spectrum .
Approach:	They propose a new classification challenge that allows for label co-occurrences without predefined limits.
Outcome:	The proposed system can handle freq-shot, few-shot and zero-shot labels without limits.

Copied to clipboard

Dehai Min, Zhiyang Xu, Guilin Qi, Lifu Huang, Chenyu You

Information Retrieval

Challenge:	Existing information retrieval models assume a homogeneous structure for knowledge sources and user queries, limiting their applicability in real-world settings.
Approach:	They propose a unified instruction-aware heterogeneous knowledge retriever that builds a heterogenous retrieval space for heterogenized knowledge and follows diverse user instructions to retrieve knowledge in specified types.
Outcome:	The proposed framework outperforms state-of-the-art methods on CompMix-IR . it achieves 6.36% relative improvements and 54.23% relative improvements .

RE2: Region-Aware Relation Extraction from Visually Rich Documents (2024.naacl-long)

Copied to clipboard

Pritika Ramu, Sijia Wang, Lalla Mouatadid, Joy Rimchala, Lifu Huang

APrompt: Attention Prompt Tuning for Efficient Adaptation of Pre-trained Language Models (2023.emnlp-main)

Challenge:	Existing studies on relation extraction from visually rich documents focus on layout structure and Optical Character Recognition (OCR) results.
Approach:	They propose a relation extraction tool that leverages layout structure among entity blocks to improve relation prediction.
Outcome:	The proposed model outperforms existing models on a wide range of domains and languages.

Copied to clipboard

Qifan Wang, Yuning Mao, Jingang Wang, Hanchao Yu, Shaoliang Nie, Sinong Wang, Fuli Feng, Lifu Huang, Xiaojun Quan, Zenglin Xu, Dongfang Liu

DiPT: Enhancing LLM Reasoning through Diversified Perspective-Taking (2025.findings-naacl)

Challenge:	Existing prompt tuning methods only introduce prompts at the input layer, limiting performance and leaving large room for improvement.
Approach:	They propose a method that involves tuning a small set of soft prompts for pre-trained language models.
Outcome:	The proposed method outperforms state-of-the-art methods with pre-trained models on the SuperGLUE benchmark.

Copied to clipboard

Hoang Anh Just, Mahavir Dabas, Lifu Huang, Ming Jin, Ruoxi Jia

New Frontiers of Information Extraction (2022.naacl-tutorials)

Challenge:	Existing work on improving language model reasoning typically explores a single solution path, which can be prone to errors.
Approach:	They propose a novel approach that incorporates diversified viewpoints into existing reasoning methods to improve their reasoning performance.
Outcome:	The proposed approach can be flexibly integrated into existing models that focus on a single reasoning approach, enhancing their reasoning performance and stability when presented with paraphrased problems.

Copied to clipboard

Muhao Chen, Lifu Huang, Manling Li, Ben Zhou, Heng Ji, Dan Roth

Multimodal Instruction Tuning with Conditional Mixture of LoRA (2024.acl-long)

Challenge:	Information extraction (IE) is the process of automatically extracting structural information from unstructured or semi-structured data.
Approach:	This tutorial will provide an introduction to recent advances in IE by answering several important research questions.
Outcome:	The tutorial will address several important research questions and outline directions for further investigation.

Copied to clipboard

Ying Shen, Zhiyang Xu, Qifan Wang, Yu Cheng, Wenpeng Yin, Lifu Huang

Navigating the Dual Facets: A Comprehensive Evaluation of Sequential Memory Editing in Large Language Models (2024.acl-long)

Challenge:	Multimodal Large Language Models (MLLMs) have demonstrated proficiency in diverse tasks across different domains.
Approach:	They propose a method that integrates multimodal instruction tuning with Conditional Mixture-of-LoRA.
Outcome:	Experimental results show that MixLoRA outperforms LoRA with the same or higher ranks . MLLMs have demonstrated remarkable proficiency in diverse tasks across domains .

Copied to clipboard

Zihao Lin, Mohammad Beigi, Hongxuan Li, Yufan Zhou, Yuxiang Zhang, Qifan Wang, Wenpeng Yin, Lifu Huang

Holistic Evaluation for Interleaved Text-and-Image Generation (2024.emnlp-main)

Challenge:	Memory Editing (ME) has emerged as an efficient method to modify erroneous facts or inject new knowledge into Large Language Models (LLMs).
Approach:	They propose to evaluate LLMs with single edit only and parameter-modifying ME with parameter-preserving ME.
Outcome:	The proposed method can maintain LLMs’ fundamental capabilities but struggles to accurately recall edited knowledge presented in a different format.

Copied to clipboard

Minqian Liu, Zhiyang Xu, Zihao Lin, Trevor Ashby, Joy Rimchala, Jiaxin Zhang, Lifu Huang

Zero-Shot Transfer Learning for Event Extraction (P18-1)

Challenge:	Existing evaluation benchmarks do not support arbitrarily interleaved images and text for both inputs and outputs.
Approach:	They propose to use a benchmark to evaluate interleaved text-and-image generation . they define five evaluation aspects for InterleavatedEval, a reference-free metric .
Outcome:	The proposed benchmarks cover a limited number of domains and use cases and lack comparableity-based metrics.

Copied to clipboard

Lifu Huang, Heng Ji, Kyunghyun Cho, Ido Dagan, Sebastian Riedel, Clare Voss

MultiInstruct: Improving Multi-Modal Zero-Shot Learning via Instruction Tuning (2023.acl-long)

Challenge:	Existing supervised event extraction methods rely on manual annotations and features specific to each event type.
Approach:	They propose a framework that maps event mentions to a specific type in an event ontology . they use existing annotations to extract event types from unstructured text data .
Outcome:	The proposed framework can be applied to new unseen event types without manual annotations.

Copied to clipboard

Zhiyang Xu, Ying Shen, Lifu Huang

R2I-Bench: Benchmarking Reasoning-Driven Text-to-Image Generation (2025.emnlp-main)

Challenge:	Experimental results show zero-shot performance on unseen multimodal tasks . instruction tuning has yet to be explored for vision and multimodal task.
Approach:	They propose a multimodal instruction tuning benchmark dataset that consists of 62 diverse multimodal tasks in a unified seq-to-seq format covering 10 broad categories.
Outcome:	The proposed model performs well on unseen multimodal tasks and is highly scalable.

Copied to clipboard

Kaijie Chen, Zihao Lin, Zhiyang Xu, Ying Shen, Yuguang Yao, Joy Rimchala, Jiaxin Zhang, Lifu Huang

Efficient Federated Learning on Knowledge Graphs via Privacy-preserving Relation Embedding Aggregation (2022.findings-emnlp)

Challenge:	Reasoning is a fundamental capability underpinning text-to-image (T2I) generation.
Approach:	They propose a benchmark to rigorously assess reasoning-driven T2I generation.
Outcome:	Experiments with 16 representative T2I models show limited reasoning performance . a strong pipeline-based framework decouples reasoning and generation .

Copied to clipboard

Kai Zhang, Yu Wang, Hongyi Wang, Lifu Huang, Carl Yang, Xun Chen, Lichao Sun

Vision-Flan: Scaling Human-Labeled Tasks in Visual Instruction Tuning (2024.findings-acl)

Challenge:	Existing frameworks that share entity embeddings of knowledge graphs (KGs) would incur a severe privacy leakage.
Approach:	They propose a new attack method that aims to recover the original embedding information based on the known entity embeddables of FedE.
Outcome:	The proposed framework can be used to infer whether a specific relation exists in a private client.

Copied to clipboard

Zhiyang Xu, Chao Feng, Rulin Shao, Trevor Ashby, Ying Shen, Di Jin, Yu Cheng, Qifan Wang, Lifu Huang

Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models (2025.findings-emnlp)

Challenge:	Recent vision-language models (VLMs) have shown impressive capabilities as general visual assistants, but there are two challenges to their performance: (1) lacking task diversity in pretraining and visual instruction tuning; (2) annotation error and bias in GPT-4 synthesized instruction tuning data.
Approach:	They propose a two-stage instruction tuning framework that fine tunes VLMs firstly and further tuned on GPT-4 synthesized data.
Outcome:	The proposed framework outperforms the traditional single-stage visual instruction tuning framework and achieves state-of-the-art performance across a wide range of multi-modal evaluation benchmarks.

Copied to clipboard

Haibo Wang, Zhiyang Xu, Yu Cheng, Shizhe Diao, Yufan Zhou, Yixin Cao, Qifan Wang, Weifeng Ge, Lifu Huang

Inference Compute-Optimal Video Vision Language Models (2025.acl-long)

Challenge:	Video Large Language Models (VLMs) have been praised for their performance in coarse-grained video understanding but still face ineffective temporal grounding and inadequate timestamp representations.
Approach:	They propose a novel Video-LLM that senses and reasoned over specific video moments with fine-grained temporal precision.
Outcome:	The proposed model surpasses existing models in fine-grained video understanding tasks and exhibits strong potential as a general video understanding assistant.

Copied to clipboard

Peiqi Wang, ShengYun Peng, Xuewen Zhang, Hanchao Yu, Yibo Yang, Lifu Huang, Fujun Liu, Qifan Wang

Visual Data in NLP

Challenge:	Using video vision language models, inference costs are often more expensive than finetuning.
Approach:	They investigate the optimal allocation of inference compute across three key scaling factors in video vision language models.
Outcome:	The proposed model configurations are based on three key scaling factors . the results can be applied to real-world tasks and tasks with fixed inference budgets.

Debate as Optimization: Adaptive Conformal Prediction and Diverse Retrieval for Event Extraction (2024.findings-emnlp)

Copied to clipboard

Sijia Wang, Lifu Huang

Biomedical Event Extraction based on Knowledge-driven Tree-LSTM (N19-1)

Challenge:	Experimental results show a significant performance gap between tuning-based approaches and event extraction approaches.
Approach:	They propose a debate as optimization system where the primary objective is to iteratively refine the large language models outputs through debating without parameter tuning.
Outcome:	The proposed system reduces performance gap between supervised approaches and tuning-free methods by 18.1% and 17.8% on ACE05 and 17.9% and 15.2% on CASIE respectively.

Copied to clipboard

Diya Li, Lifu Huang, Heng Ji, Jiawei Han

EAVE: Efficient Product Attribute Value Extraction via Lightweight Sparse-layer Interaction (2024.findings-emnlp)

Challenge:	Biomedical event extraction requires domain-specific knowledge and deep understanding of complex contexts.
Approach:	They propose a knowledge base-driven tree-structured long short-term memory networks framework . tree-LSTM framework incorporates dependency structures and entity properties from ontologies .
Outcome:	The proposed framework is based on the BioNLP shared task with Genia dataset and achieves state-of-the-art results.

Copied to clipboard

Li Yang, Qifan Wang, Jianfeng Chi, Jiahao Liu, Jingang Wang, Fuli Feng, Zenglin Xu, Yi Fang, Lifu Huang, Dongfang Liu

Sycophancy Mitigation Through Reinforcement Learning with Uncertainty-Aware Adaptive Reasoning Trajectories (2025.emnlp-main)

Challenge:	Existing methods to extract product attribute value require multiple extractions to obtain all corresponding values.
Approach:	They propose an Efficient product Attribute Value Extraction approach using lightweight sparse-layer interaction.
Outcome:	The proposed method achieves significant efficiency gains with neutral or marginal loss in performance when the context is long and number of attributes is large.

Copied to clipboard

Mohammad Beigi, Ying Shen, Parshin Shojaee, Qifan Wang, Zichao Wang, Chandan K. Reddy, Ming Jin, Lifu Huang

Reasoning

Challenge:	Existing studies show that large language models inadvertently foster sycophancy . scophancies are a tendency of models to blindly conform to user preferences without critical reasoning or self-reflection.
Approach:	They propose a method to reduce sycophancy by combining uncertainty-aware Monte Carlo tree search and progress-based reinforcement learning.
Outcome:	The proposed model outperforms baseline models in effectively reducing sycophancy while maintaining performance on out-of-distribution inputs.

DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models (2024.emnlp-main)

Copied to clipboard

Yiming Huang, Jianwen Luo, Yan Yu, Yitong Zhang, Fangyu Lei, Yifan Wei, Shizhu He, Lifu Huang, Xiao Liu, Jun Zhao, Kang Liu

Programming Languages in NLP

Challenge:	DA-Code is a code generation benchmark designed to assess LLMs on agent-based data science tasks.
Approach:	They propose a code generation benchmark specifically designed for LLMs on agent-based data science tasks.
Outcome:	The benchmark performs better than existing frameworks, but lacks accuracy . it is based on real-world data, and includes examples that cover a wide range of tasks .

Multimedia Generative Script Learning for Task Planning (2023.findings-acl)

Copied to clipboard

Qingyun Wang, Manling Li, Hou Pong Chan, Lifu Huang, Julia Hockenmaier, Girish Chowdhary, Heng Ji

Genre Separation Network with Adversarial Training for Cross-genre Relation Extraction (D18-1)

Challenge:	Goal-oriented generative script learning aims to generate subsequent steps to reach a specific goal . ability to capture historical states in visual modalities provides detailed information not covered by text .
Approach:	They propose a goal-oriented generative script learning task to generate subsequent steps by tracking historical states in both text and vision modalities.
Outcome:	The proposed task outperforms baselines in three aspects of the current task.

Copied to clipboard

Ge Shi, Chong Feng, Lifu Huang, Boliang Zhang, Heng Ji, Lejian Liao, Heyan Huang

Robustness in NLP

Challenge:	Existing methods to extract genre-specific and genre-agnostic features require great human effort.
Approach:	They propose to use two encoders to explicitly extract genre-specific and genre-agnostic features.
Outcome:	The proposed approach outperforms the state-of-the-art by 1.7% on three distinct genres.

Multi-lingual Common Semantic Space Construction via Cluster-consistent Word Embedding (D18-1)

Copied to clipboard

Lifu Huang, Kyunghyun Cho, Boliang Zhang, Heng Ji, Kevin Knight

Semantic Text Processing

Challenge:	a new approach to multilingual word embedding is needed to achieve this goal . a multilingual common semantic space is a language-agnostic semantic continuous space .
Approach:	They propose a multilingual common semantic space where words from multiple languages are mapped into a shared space so that resources and knowledge can be shared across languages.
Outcome:	The proposed approach achieves 14.6% absolute F-score gain over state-of-the-art methods on cross-lingual direct transfer.

PaperRobot: Incremental Draft Generation of Scientific Ideas (P19-1)

Copied to clipboard

Qingyun Wang, Lifu Huang, Zhiying Jiang, Kevin Knight, Heng Ji, Mohit Bansal, Yi Luan

Structured Data in NLP

Challenge:	a paper robot can read existing papers and create new nodes or links in the knowledge graphs.
Approach:	They propose to automate the creation of new ideas by predicting links from the background KGs.
Outcome:	The proposed paper automates three tasks: read existing papers, create new ideas, predict links . the paper generated abstracts, conclusion and future work sections, and new titles are chosen over human-written ones up to 30%, 24% and 12% of the time.

RoAST: Robustifying Language Models via Adversarial Perturbation with Selective Training (2023.findings-emnlp)

Copied to clipboard

Jaehyung Kim, Yuning Mao, Rui Hou, Hanchao Yu, Davis Liang, Pascale Fung, Qifan Wang, Fuli Feng, Lifu Huang, Madian Khabsa

Robustness in NLP

Challenge:	Several perspectives of robustness for pre-trained language models have been studied independently, but lacking a unified consideration in multiple perspectives.
Approach:	They propose a technique to enhance the multi-perspective robustness of LMs by introducing adversarial perturbation while the model parameters are selectively updated upon their relative importance.
Outcome:	The proposed technique improves the robustness of LMs by incorporating four perspectives on model robustness.

Error-driven Data-efficient Large Multimodal Model Tuning (2025.acl-long)

Copied to clipboard

Barry Menglong Yao, Qifan Wang, Lifu Huang