Author name cluster

Houfeng Wang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

14 papers

2 author rows

NeurIPS Conference 2025 Conference Paper

Sheetpedia: A 300K-Spreadsheet Corpus for Spreadsheet Intelligence and LLM Fine-Tuning

Zailong Tian
Zhuoheng Han
Houfeng Wang
Lizi Liao

Spreadsheets are widely used for data analysis and reporting, yet their complex structure and formula logic pose significant challenges for AI systems. We introduce Sheetpedia, a large-scale corpus of over 290, 000 diverse spreadsheets (from 324, 000+ workbooks) compiled from enterprise email archives and online forums. We detail a rigorous collection and preprocessing pipeline (integrating the Enron email spreadsheet archive and the Fuse web corpus, plus a new crawl of Excel forums) to standardize formats, filter languages, and remove duplicates. Sheetpedia provides extensive coverage of real formulas and annotations – addressing a gap left by prior table datasets (e. g. web tables used in TURL or Text-to-SQL in Spider) which often lack formula semantics. We present comprehensive corpus statistics, highlighting rich formula diversity and a majority (78\%+) of English content. To demonstrate the corpus’s utility, we fine-tune large language models on Sheetpedia for two novel spreadsheet understanding tasks: Natural Language to Semantic Range (NL2SR) and Natural Language to Formula (NL2Formula). Using a rejection-sampling data generation strategy, our fine-tuned models achieve up to 97. 5\% accuracy on NL2SR and 71. 7\% on NL2Formula – substantially outperforming baseline approaches. Sheetpedia (to be released publicly) fills a crucial need for a large, high-quality spreadsheet benchmark, enabling more effective spreadsheet intelligence and natural language interfaces for spreadsheet tools.

PDF Details

NeurIPS Conference 2025 Conference Paper

TimE: A Multi-level Benchmark for Temporal Reasoning of LLMs in Real-World Scenarios

Shaohang Wei
Wei Li
Feifan Song
Wen Luo
Tianyi Zhuang
Haochen Tan
Zhijiang Guo
Houfeng Wang

Temporal reasoning is pivotal for Large Language Models (LLMs) to comprehend the real world. However, existing works neglect the real-world challenges for temporal reasoning: (1) intensive temporal information, (2) fast-changing event dynamics, and (3) complex temporal dependencies in social interactions. To bridge this gap, we propose a multi-level benchmark TimE, designed for temporal reasoning in real-world scenarios. TimE consists of 38, 522 QA pairs, covering 3 levels with 11 fine-grained sub-tasks. This benchmark encompasses 3 sub-datasets reflecting different real-world challenges: TimE-Wiki, TimE-News, and TimE-Dial. We conduct extensive experiments on reasoning models and non-reasoning models. And we conducted an in-depth analysis of temporal reasoning performance across diverse real-world scenarios and tasks, and summarized the impact of test-time scaling on temporal reasoning capabilities. Additionally, we release TimE-Lite, a human-annotated subset to foster future research and standardized evaluation in temporal reasoning.

PDF Details

AAAI Conference 2024 Conference Paper

Preference Ranking Optimization for Human Alignment

Feifan Song
Bowen Yu
Minghao Li
Haiyang Yu
Fei Huang
Yongbin Li
Houfeng Wang

Large language models (LLMs) often contain misleading content, emphasizing the need to align them with human values to ensure secure AI systems. Reinforcement learning from human feedback (RLHF) has been employed to achieve this alignment. However, it encompasses two main drawbacks: (1) RLHF exhibits complexity, instability, and sensitivity to hyperparameters in contrast to SFT. (2) Despite massive trial-and-error, multiple sampling is reduced to pair-wise contrast, thus lacking contrasts from a macro perspective. In this paper, we propose Preference Ranking Optimization (PRO) as an efficient SFT algorithm to directly fine-tune LLMs for human alignment. PRO extends the pair-wise contrast to accommodate preference rankings of any length. By iteratively contrasting candidates, PRO instructs the LLM to prioritize the best response while progressively ranking the rest responses. In this manner, PRO effectively transforms human alignment into aligning the probability ranking of n responses generated by LLM with the preference ranking of humans towards these responses. Experiments have shown that PRO outperforms baseline algorithms, achieving comparable results to ChatGPT and human responses through automatic-based, reward-based, GPT-4, and human evaluations.

PDF Details DOI

IJCAI Conference 2022 Conference Paper

A Unified Strategy for Multilingual Grammatical Error Correction with Pre-trained Cross-Lingual Language Model

Xin Sun
Tao Ge
Shuming Ma
Jingjing Li
Furu Wei
Houfeng Wang

Synthetic data construction of Grammatical Error Correction (GEC) for non-English languages relies heavily on human-designed and language-specific rules, which produce limited error-corrected patterns. In this paper, we propose a generic and language-independent strategy for multilingual GEC, which can train a GEC system effectively for a new non-English language with only two easy-to-access resources: 1) a pre-trained cross-lingual language model (PXLM) and 2) parallel translation data between English and the language. Our approach creates diverse parallel GEC data without any language-specific operations by taking the non-autoregressive translation generated by PXLM and the gold translation as error-corrected sentence pairs. Then, we reuse PXLM to initialize the GEC model and pre-train it with the synthetic data generated by itself, which yields further improvement. We evaluate our approach on three public benchmarks of GEC in different languages. It achieves the state-of-the-art results on the NLPCC 2018 Task 2 dataset (Chinese) and obtains competitive performance on Falko-Merlin (German) and RULEC-GEC (Russian). Further analysis demonstrates that our data construction method is complementary to rule-based approaches.

PDF Details DOI

AAAI Conference 2022 Conference Paper

Confidence Calibration for Intent Detection via Hyperspherical Space and Rebalanced Accuracy-Uncertainty Loss

Yantao Gong
Cao Liu
Fan Yang
Xunliang Cai
Guanglu Wan
Jiansong Chen
Weipeng Zhang
Houfeng Wang

Data-driven methods have achieved notable performance on intent detection, which is a task to comprehend user queries. Nonetheless, they are controversial for over-confident predictions. In some scenarios, users do not only care about the accuracy but also the confidence of model. Unfortunately, mainstream neural networks are poorly calibrated, with a large gap between accuracy and confidence. To handle this problem defined as confidence calibration, we propose a model using the hyperspherical space and rebalanced accuracy-uncertainty loss. Specifically, we project the label vector onto hyperspherical space uniformly to generate a dense label representation matrix, which mitigates over-confident predictions due to overfitting sparce one-hot label matrix. Besides, we rebalance samples of different accuracy and uncertainty to better guide model training. Experiments on the open datasets verify that our model outperforms the existing calibration methods and achieves a significant improvement on the calibration metric.

PDF Details

AAAI Conference 2021 Conference Paper

Towards Semantics-Enhanced Pre-Training: Can Lexicon Definitions Help Learning Sentence Meanings?

Xuancheng Ren
Xu Sun
Houfeng Wang
Qun Liu

Self-supervised pre-training techniques, albeit relying on large amounts of text, have enabled rapid growth in learning language representations for natural language understanding. However, as radically empirical models on sentences, they are subject to the input data distribution, inevitably incorporating data bias and reporting bias, which may lead to inaccurate understanding of sentences. To address this problem, we propose to adopt a human learner’s approach: when we cannot make sense of a word in a sentence, we often consult the dictionary for specific meanings; but can the same work for empirical models? In this work, we try to inform the pre-trained masked language models of word meanings for semantics-enhanced pre-training. To achieve a contrastive and holistic view of word meanings, a definition pair of two related words is presented to the masked language model such that the model can better associate a word with its crucial semantic features. Both intrinsic and extrinsic evaluations validate the proposed approach on semantics-orientated tasks, with an almost negligible increase of training data.

PDF Details

AAAI Conference 2020 Conference Paper

Graph LSTM with Context-Gated Mechanism for Spoken Language Understanding

Linhao Zhang
Dehong Ma
Xiaodong Zhang
Xiaohui Yan
Houfeng Wang

Much research in recent years has focused on spoken language understanding (SLU), which usually involves two tasks: intent detection and slot ﬁlling. Since Yao et al. (2013), almost all SLU systems are RNN-based, which have been shown to suffer various limitations due to their sequential nature. In this paper, we propose to tackle this task with Graph LSTM, which ﬁrst converts text into a graph and then utilizes the message passing mechanism to learn the node representation. Not only the Graph LSTM addresses the limitations of sequential models, but it can also help to utilize the semantic correlation between slot and intent. We further propose a context-gated mechanism to make better use of context information for slot ﬁlling. Our extensive evaluation shows that the proposed model outperforms the state-of-the-art results by a large margin.

PDF Details

AAAI Conference 2020 Conference Paper

MaskGEC: Improving Neural Grammatical Error Correction via Dynamic Masking

Zewei Zhao
Houfeng Wang

Grammatical error correction (GEC) is a promising natural language processing (NLP) application, whose goal is to change the sentences with grammatical errors into the correct ones. Neural machine translation (NMT) approaches have been widely applied to this translation-like task. However, such methods need a fairly large parallel corpus of errorannotated sentence pairs, which is not easy to get especially in the ﬁeld of Chinese grammatical error correction. In this paper, we propose a simple yet effective method to improve the NMT-based GEC models by dynamic masking. By adding random masks to the original source sentences dynamically in the training procedure, more diverse instances of errorcorrected sentence pairs are generated to enhance the generalization ability of the grammatical error correction model without additional data. The experiments on NLPCC 2018 Task 2 show that our MaskGEC model improves the performance of the neural GEC models. Besides, our single model for Chinese GEC outperforms the current state-of-the-art ensemble system in NLPCC 2018 Task 2 without any extra knowledge.

PDF Details

AAAI Conference 2018 Conference Paper

Duplicate Question Identification by Integrating FrameNet With Neural Networks

Xiaodong Zhang
Xu Sun
Houfeng Wang

There are two major problems in duplicate question identiﬁcation, namely lexical gap and essential constituents matching. Previous methods either design various similarity features or learn representations via neural networks, which try to solve the lexical gap but neglect the essential constituents matching. In this paper, we focus on the essential constituents matching problem and use FrameNet-style semantic parsing to tackle it. Two approaches are proposed to integrate FrameNet parsing with neural networks. An ensemble approach combines a traditional model with manually designed features and a neural network model. An embedding approach converts frame parses to embeddings, which are combined with word embeddings at the input of neural networks. Experiments on Quora question pairs dataset demonstrate that the ensemble approach is more effective and outperforms all baselines. 1

PDF Details

AAAI Conference 2017 Conference Paper

Attentive Interactive Neural Networks for Answer Selection in Community Question Answering

Xiaodong Zhang
Sujian Li
Lei Sha
Houfeng Wang

Answer selection plays a key role in community question answering (CQA). Previous research on answer selection usually ignores the problems of redundancy and noise prevalent in CQA. In this paper, we propose to treat different text segments differently and design a novel attentive interactive neural network (AI-NN) to focus on those text segments useful to answer selection. The representations of question and answer are ﬁrst learned by convolutional neural networks (CNNs) or other neural network architectures. Then AI-NN learns interactions of each paired segments of two texts. Row-wise and column-wise pooling are used afterwards to collect the interactions. We adopt attention mechanism to measure the importance of each segment and combine the interactions to obtain ﬁxed-length representations for question and answer. Experimental results on CQA dataset in SemEval-2016 demonstrate that AI-NN outperforms state-of-the-art method.

PDF Details

IJCAI Conference 2017 Conference Paper

Interactive Attention Networks for Aspect-Level Sentiment Classification

Dehong Ma
Sujian Li
Xiaodong Zhang
Houfeng Wang

Aspect-level sentiment classification aims at identifying the sentiment polarity of specific target in its context. Previous approaches have realized the importance of targets in sentiment classification and developed various methods with the goal of precisely modeling thier contexts via generating target-specific representations. However, these studies always ignore the separate modeling of targets. In this paper, we argue that both targets and contexts deserve special treatment and need to be learned their own representations via interactive learning. Then, we propose the interactive attention networks (IAN) to interactively learn attentions in the contexts and targets, and generate the representations for targets and contexts separately. With this design, the IAN model can well represent a target and its collocative context, which is helpful to sentiment classification. Experimental results on SemEval 2014 Datasets demonstrate the effectiveness of our model.

PDF Details

ICML Conference 2017 Conference Paper

meProp: Sparsified Back Propagation for Accelerated Deep Learning with Reduced Overfitting

Xu Sun 0001
Xuancheng Ren
Shuming Ma
Houfeng Wang

We propose a simple yet effective technique for neural network learning. The forward propagation is computed as usual. In back propagation, only a small subset of the full gradient is computed to update the model parameters. The gradient vectors are sparsified in such a way that only the top-$k$ elements (in terms of magnitude) are kept. As a result, only $k$ rows or columns (depending on the layout) of the weight matrix are modified, leading to a linear reduction ($k$ divided by the vector dimension) in the computational cost. Surprisingly, experimental results demonstrate that we can update only 1–4\% of the weights at each back propagation pass. This does not result in a larger number of training iterations. More interestingly, the accuracy of the resulting models is actually improved rather than degraded, and a detailed analysis is given.

Details

IJCAI Conference 2016 Conference Paper

A Joint Model of Intent Determination and Slot Filling for Spoken Language Understanding

Xiaodong Zhang
Houfeng Wang

Two major tasks in spoken language understanding (SLU) are intent determination (ID) and slot filling (SF). Recurrent neural networks (RNNs) have been proved effective in SF, while there is no prior work using RNNs in ID. Based on the idea that the intent and semantic slots of a sentence are correlative, we propose a joint model for both tasks. Gated recurrent unit (GRU) is used to learn the representation of each time step, by which the label of each slot is predicted. Meanwhile, a max-pooling layer is employed to capture global features of a sentence for intent classification. The representations are shared by two tasks and the model is trained by a united loss function. We conduct experiments on two datasets, and the experimental results demonstrate that our model outperforms the state-of-the-art approaches on both tasks.

PDF Details

IJCAI Conference 2016 Conference Paper

Collaborative Filtering with Generalized Laplacian Constraint via Overlapping Decomposition

Qing Zhang
Houfeng Wang

Real-world data are seldom unstructured, yet traditional Matrix Factorization (MF) models, as one of the most powerful collaborative filtering approaches, generally rely on this assumption to recover the low-rank structures for recommendation. However, few of them are able to explicitly consider structured constraint with the underlying low-rank assumption to model complex user interests. To solve this problem, we propose a unified MF framework with generalized Laplacian constraint for collaborative filtering. We investigate the connection between the recently proposed Laplacian constraint and the classical normalized cut problem, and make it possible to extend the original non-overlapping prior, to capture the overlapping case via learning the decomposed multi-facet graphs. Experiments on real-world datasets demonstrate the effectiveness of the proposed method.

PDF Details