AIConfPaper
← Search

Tianqing Fang

33 accepted papers

2026

NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agents

Tianshi Zheng, Kelvin Kiu Wai Tam, Newt Nguyen Kim Hue Nam, Baixuan Xu, Zhaowei Wang, Cheng Jiayang +7
ICLR 2026poster

Large language models (LLMs) are emerging as powerful tools for scientific law discovery, a foundational challenge in AI-driven science. However, existing benchmarks for this task suffer from a fundamental methodological trilemma, forcing a trade-off between scientific relevance, scalability, and re…

Cited by 0Source ↗Scholar ↗
2026

WebDevJudge: Evaluating (M)LLMs as Critiques for Web Development Quality

Chunyang Li, Yilun Zheng, Xinting Huang, Tianqing Fang, Jiahao Xu, Lihui Chen +2
ICLR 2026oral

The paradigm of LLM-as-a-judge is emerging as a scalable and efficient alternative to human evaluation, demonstrating strong performance on well-defined tasks. However, its reliability in open-ended tasks with dynamic environments and complex interactions remains unexplored. To bridge the gap, we in…

Cited by 0Source ↗code ↗Scholar ↗
2025

Attention Entropy is a Key Factor: An Analysis of Parallel Context Encoding with Full-attention-based Pre-trained Language Models

Zhisong Zhang, Yan Wang, Xinting Huang, Tianqing Fang, Hongming Zhang, Chenlong Deng +2
ACL 2025long

Large language models have shown remarkable performance across a wide range of language tasks, owing to their exceptional capabilities in context modeling. The most commonly used method of context modeling is full self-attention, as seen in standard decoder-only Transformers. Although powerful, this…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

ConKE: Conceptualization-Augmented Knowledge Editing in Large Language Models for Commonsense Reasoning

Liyu Zhang, Weiqi Wang, Tianqing Fang, Yangqiu Song
ACL 2025finding

Knowledge Editing (KE) aims to adjust a Large Language Model’s (LLM) internal representations and parameters to correct inaccuracies and improve output consistency without incurring the computational expense of re-training the entire model. However, editing commonsense knowledge still faces difficul…

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

Concept-Reversed Winograd Schema Challenge: Evaluating and Improving Robust Reasoning in Large Language Models via Abstraction

Kaiqiao Han, Tianqing Fang, Zhaowei Wang, Yangqiu Song, Mark Steedman
NAACL 2025short

While Large Language Models (LLMs) have showcased remarkable proficiency in reasoning, there is still a concern about hallucinations and unreliable reasoning issues due to semantic associations and superficial logical chains. To evaluate the extent to which LLMs perform robust reasoning instead of r…

Cited by 3Source ↗PDF ↗code ↗Scholar ↗
2025

DivScene: Towards Open-Vocabulary Object Navigation with Large Vision Language Models in Diverse Scenes

Zhaowei Wang, Hongming Zhang, Tianqing Fang, Ye Tian, Yue Yang, Kaixin Ma +3
EMNLP 2025

Large Vision-Language Models (LVLMs) have achieved significant progress in tasks like visual question answering and document understanding. However, their potential to comprehend embodied environments and navigate within them remains underexplored. In this work, we first study the challenge of open-

Cited by 0Source ↗PDF ↗Scholar ↗
2025

On the Role of Entity and Event Level Conceptualization in Generalizable Reasoning: A Survey of Tasks, Methods, Applications, and Future Directions

Weiqi Wang, Tianqing Fang, Haochen Shi, Baixuan Xu, Wenxuan Ding, Liyu Zhang +5
EMNLP 2025

Conceptualization, a fundamental element of human cognition, plays a pivotal role in human generalizable reasoning.Generally speaking, it refers to the process of sequentially abstracting specific instances into higher-level concepts and then forming abstract knowledge that can be applied in unfamil

Cited by 0Source ↗PDF ↗Scholar ↗
2025

OpenWebVoyager: Building Multimodal Web Agents via Iterative Real-World Exploration, Feedback and Optimization

Hongliang He, Wenlin Yao, Kaixin Ma, Wenhao Yu, Hongming Zhang, Tianqing Fang +2
ACL 2025long

The advancement of foundation models has laid the groundwork for building autonomous agents for complex tasks such as web navigation. Recent efforts have also tried to equip the agent with the ability to explore environments and continuously improve over time. However, existing works only focused on…

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

Recall with Reasoning: Chain-of-Thought Distillation for Mamba’s Long-Context Memory and Extrapolation

Jun-Yu Ma, Tianqing Fang, Zhisong Zhang, Hongming Zhang, Haitao Mi, Dong Yu
EMNLP 2025

Mamba’s theoretical infinite-context potential is limited in practice when sequences far exceed training lengths. This work explores unlocking Mamba’s long-context memory ability by a simple-yet-effective method, Recall with Reasoning (RwR), by distilling chain-of-thought (CoT) summarization from a

Cited by 0Source ↗PDF ↗Scholar ↗
2025

UniGist: Towards General and Hardware-aligned Sequence-level Long Context Compression

Chenlong Deng, Zhisong Zhang, Kelong Mao, Shuaiyi Li, Tianqing Fang, Hongming Zhang +3
NeurIPS 2025poster

Large language models are increasingly capable of handling long-context inputs, but the memory overhead of KV cache remains a major bottleneck for general-purpose deployment. While many compression strategies have been explored, sequence-level compression is particularly challenging due to its tende…

Cited by 0Source ↗Scholar ↗
2025

WebCoT: Enhancing Web Agent Reasoning by Reconstructing Chain-of-Thought in Reflection, Branching, and Rollback

Minda Hu, Tianqing Fang, Jianshu Zhang, Jun-Yu Ma, Zhisong Zhang, Jingyan Zhou +4
EMNLP 2025

Web agents powered by Large Language Models (LLMs) show promise for next-generation AI, but their limited reasoning in uncertain, dynamic web environments hinders robust deployment. In this paper, we identify key reasoning skills essential for effective web agents, i.e., reflection & lookahead, bran

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

WebEvolver: Enhancing Web Agent Self-Improvement with Co-evolving World Model

Tianqing Fang, Hongming Zhang, Zhisong Zhang, Kaixin Ma, Wenhao Yu, Haitao Mi +1
EMNLP 2025

Agent self-improvement, where agents autonomously train their underlying Large Language Model (LLM) on self-sampled trajectories, shows promising results but often stagnates in web environments due to limited exploration and under-utilization of pretrained web knowledge. To improve the performance o

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

AbsInstruct: Eliciting Abstraction Ability from LLMs through Explanation Tuning with Plausibility Estimation

Zhaowei Wang, Wei Fan, Qing Zong, Hongming Zhang, Sehyun Choi, Tianqing Fang +4
ACL 2024long

Abstraction ability is crucial in human intelligence, which can also benefit various tasks in NLP study. Existing work shows that LLMs are deficient in abstract ability, and how to improve it remains unexplored. In this work, we design the framework AbsInstruct to enhance LLMs’ abstraction ability t…

Cited by 8Source ↗PDF ↗code ↗Scholar ↗
2024

AbsPyramid: Benchmarking the Abstraction Ability of Language Models with a Unified Entailment Graph

Zhaowei Wang, Haochen Shi, Weiqi Wang, Tianqing Fang, Hongming Zhang, Sehyun Choi +2
NAACL 2024findings

Cognitive research indicates that abstraction ability is essential in human intelligence, which remains under-explored in language models. In this paper, we present AbsPyramid, a unified entailment graph of 221K textual descriptions of abstraction knowledge. While existing resources only touch nouns…

Cited by 16Source ↗PDF ↗code ↗Scholar ↗
2024

CANDLE: Iterative Conceptualization and Instantiation Distillation from Large Language Models for Commonsense Reasoning

Weiqi Wang, Tianqing Fang, Chunyang Li, Haochen Shi, Wenxuan Ding, Baixuan Xu +6
ACL 2024long

The sequential process of conceptualization and instantiation is essential to generalizable commonsense reasoning as it allows the application of existing knowledge to unfamiliar scenarios. However, existing works tend to undervalue the step of instantiation and heavilyrely on pre-built concept taxo…

Cited by 21Source ↗PDF ↗code ↗Scholar ↗
2024

Complex Reasoning over Logical Queries on Commonsense Knowledge Graphs

Tianqing Fang, Zeming Chen, Yangqiu Song, Antoine Bosselut
ACL 2024long

Event commonsense reasoning requires the ability to reason about the relationship between events, as well as infer implicit contextunderlying that relationship. However, data scarcity makes it challenging for language models to learn to generate commonsense infer-ences for contexts and questions inv…

Cited by 10Source ↗PDF ↗code ↗Scholar ↗
2024

Getting Sick After Seeing a Doctor? Diagnosing and Mitigating Knowledge Conflicts in Event Temporal Reasoning

Tianqing Fang, Zhaowei Wang, Wenxuan Zhou, Hongming Zhang, Yangqiu Song, Muhao Chen
NAACL 2024findings

Event temporal reasoning aims at identifying the temporal relations between two or more events from narratives. However, knowledge conflicts arise when there is a mismatch between the actual temporal relations of events in the context and the prior knowledge or biases learned by the model. In this p…

Cited by 10Source ↗PDF ↗code ↗Scholar ↗
2024

IntentionQA: A Benchmark for Evaluating Purchase Intention Comprehension Abilities of Language Models in E-commerce

Wenxuan Ding, Weiqi Wang, Sze Heng Douglas Kwok, Minghao Liu, Tianqing Fang, Jiaxin Bai +8
EMNLP 2024finding

Enhancing Language Models’ (LMs) ability to understand purchase intentions in E-commerce scenarios is crucial for their effective assistance in various downstream tasks. However, previous approaches that distill intentions from LMs often fail to generate meaningful and human-centric intentions appli…

Cited by 6Source ↗PDF ↗code ↗Scholar ↗
2024

MIND: Multimodal Shopping Intention Distillation from Large Vision-language Models for E-commerce Purchase Understanding

Baixuan Xu, Weiqi Wang, Haochen Shi, Wenxuan Ding, Huihao Jing, Tianqing Fang +9
EMNLP 2024main

Improving user experience and providing personalized search results in E-commerce platforms heavily rely on understanding purchase intention. However, existing methods for acquiring large-scale intentions bank on distilling large language models with human annotation for verification. Such an approa…

Cited by 7Source ↗PDF ↗code ↗Scholar ↗
2024

Neuro-Inspired Information-Theoretic Hierarchical Perception for Multimodal Learning

Xiongye Xiao, Gengshuo Liu, Gaurav Gupta, Defu Cao, Shixuan Li, Yaxing Li +3
ICLR 2024poster

Integrating and processing information from various sources or modalities are critical for obtaining a comprehensive and accurate perception of the real world in autonomous systems and cyber-physical systems. Drawing inspiration from neuroscience, we develop the Information-Theoretic Hierarchical Pe…

Cited by 15Source ↗PDF ↗code ↗Scholar ↗
2023

CAR: Conceptualization-Augmented Reasoner for Zero-Shot Commonsense Question Answering

Weiqi Wang, Tianqing Fang, Wenxuan Ding, Baixuan Xu, Xin Liu, Yangqiu Song +1
EMNLP 2023long findings

The task of zero-shot commonsense question answering evaluates models on their capacity to reason about general scenarios beyond those presented in specific datasets. Existing approaches for tackling this task leverage external knowledge from CommonSense Knowledge Bases (CSKBs) by pre-training the m…

Cited by 0Source ↗code ↗Scholar ↗
2023

CAT: A Contextualized Conceptualization and Instantiation Framework for Commonsense Reasoning

Weiqi Wang, Tianqing Fang, Baixuan Xu, Chun Yi Louis Bo, Yangqiu Song, Lei Chen
ACL 2023long

Commonsense reasoning, aiming at endowing machines with a human-like ability to make situational presumptions, is extremely challenging to generalize. For someone who barely knows about “meditation,” while is knowledgeable about “singing,” he can still infer that “meditation makes people relaxed” fr…

Cited by 28Source ↗PDF ↗code ↗Scholar ↗
2023

COLA: Contextualized Commonsense Causal Reasoning from the Causal Inference Perspective

Zhaowei Wang, Quyet V. Do, Hongming Zhang, Jiayao Zhang, Weiqi Wang, Tianqing Fang +3
ACL 2023long

Detecting commonsense causal relations (causation) between events has long been an essential yet challenging task. Given that events are complicated, an event may have different causes under various contexts. Thus, exploiting context plays an essential role in detecting causal relations. Meanwhile,…

Cited by 17Source ↗PDF ↗code ↗Scholar ↗
2023

Doolittle: Benchmarks and Corpora for Academic Writing Formalization

Shizhe Diao, Yongyu Lei, Liangming Pan, Tianqing Fang, Wangchunshu Zhou, Sedrick Scott Keh +2
EMNLP 2023long main

Improving the quality of academic writing is a meaningful but challenging task. Conventional methods of language refinement focus on narrow, specific linguistic features within isolated sentences, such as grammatical errors and improper word use. We propose a more general task, Academic Writing Form…

Cited by 0Source ↗Scholar ↗
2023

KCTS: Knowledge-Constrained Tree Search Decoding with Token-Level Hallucination Detection

Sehyun Choi, Tianqing Fang, Zhaowei Wang, Yangqiu Song
EMNLP 2023long main

Large Language Models (LLMs) have demonstrated remarkable human-level natural language generation capabilities. However, their potential to generate misinformation, often called the *hallucination* problem, poses a significant risk to their deployment. A common approach to address this issue is to r…

Cited by 0Source ↗code ↗Scholar ↗
2023

QADYNAMICS: Training Dynamics-Driven Synthetic QA Diagnostic for Zero-Shot Commonsense Question Answering

Haochen Shi, Weiqi Wang, Tianqing Fang, Baixuan Xu, Wenxuan Ding, Xin Liu +1
EMNLP 2023short findings

Zero-shot commonsense Question-Answering (QA) requires models to reason about general situations beyond specific benchmarks. State-of-the-art approaches fine-tune language models on QA pairs constructed from CommonSense Knowledge Bases (CSKBs) to equip the models with more commonsense knowledge in a…

Cited by 0Source ↗code ↗Scholar ↗
2023

StoryAnalogy: Deriving Story-level Analogies from Large Language Models to Unlock Analogical Understanding

Cheng Jiayang, Lin Qiu, Tsz Ho CHAN, Tianqing Fang, Weiqi Wang, Chunkit Chan +6
EMNLP 2023long main

Analogy-making between narratives is crucial for human reasoning. In this paper, we evaluate the ability to identify and generate analogies by constructing a first-of-its-kind large-scale story-level analogy corpus, \textsc{StoryAnalogy}, which contains 24K story pairs from diverse domains with huma…

Cited by 0Source ↗code ↗Scholar ↗
2022

MICO: A Multi-alternative Contrastive Learning Framework for Commonsense Knowledge Representation

Ying Su, Zihao Wang, Tianqing Fang, Hongming Zhang, Yangqiu Song, Tong Zhang
EMNLP 2022finding

Commonsense reasoning tasks such as commonsense knowledge graph completion and commonsense question answering require powerful representation learning. In this paper, we propose to learn commonsense knowledge representation by MICO, a Multi-alternative contrastIve learning framework on COmmonsense k…

Cited by 12Source ↗PDF ↗code ↗Scholar ↗
2022

PseudoReasoner: Leveraging Pseudo Labels for Commonsense Knowledge Base Population

Tianqing Fang, Quyet V. Do, Hongming Zhang, Yangqiu Song, Ginny Y. Wong, Simon See
EMNLP 2022finding

Commonsense Knowledge Base (CSKB) Population aims at reasoning over unseen entities and assertions on CSKBs, and is an important yet hard commonsense reasoning task. One challenge is that it requires out-of-domain generalization ability as the source CSKB for training is of a relatively smaller scal…

Cited by 8Source ↗PDF ↗code ↗Scholar ↗
2022

SubeventWriter: Iterative Sub-event Sequence Generation with Coherence Controller

Zhaowei Wang, Hongming Zhang, Tianqing Fang, Yangqiu Song, Ginny Wong, Simon See
EMNLP 2022main

In this paper, we propose a new task of sub-event generation for an unseen process to evaluate the understanding of the coherence of sub-event actions and objects. To solve the problem, we design SubeventWriter, a sub-event sequence generation framework with a coherence controller. Given an unseen p…

Cited by 10Source ↗PDF ↗code ↗Scholar ↗
2022

Weakly Supervised Text Classification using Supervision Signals from a Language Model

Ziqian Zeng, Weimin Ni, Tianqing Fang, Xiang Li, Xinran Zhao, Yangqiu Song
NAACL 2022findings

Solving text classification in a weakly supervised manner is important for real-world applications where human annotations are scarce. In this paper, we propose to query a masked language model with cloze style prompts to obtain supervision signals. We design a prompt which combines the document its…

Cited by 19Source ↗PDF ↗code ↗Scholar ↗
2021

Benchmarking Commonsense Knowledge Base Population with an Effective Evaluation Dataset

Tianqing Fang, Weiqi Wang, Sehyun Choi, Shibo Hao, Hongming Zhang, Yangqiu Song +1
EMNLP 2021main

Reasoning over commonsense knowledge bases (CSKB) whose elements are in the form of free-text is an important yet hard task in NLP. While CSKB completion only fills the missing links within the domain of the CSKB, CSKB population is alternatively proposed with the goal of reasoning unseen assertions…

Cited by 23Source ↗PDF ↗code ↗Scholar ↗
2021

Probing Toxic Content in Large Pre-Trained Language Models

Nedjma Ousidhoum, Xinran Zhao, Tianqing Fang, Yangqiu Song, Dit-Yan Yeung
ACL 2021long

Large pre-trained language models (PTLMs) have been shown to carry biases towards different social groups which leads to the reproduction of stereotypical and toxic content by major NLP systems. We propose a method based on logistic regression classifiers to probe English, French, and Arabic PTLMs a…

Cited by 135Source ↗PDF ↗code ↗Scholar ↗