Nan Xu

Nan Xu, Fei Wang, Bangzheng Li et al.

Entity typing aims at predicting one or more words that describe the type(s) of a specific mention in a sentence. Due to shortcuts from surface patterns to annotated entity labels and biased training, existing entity typing models are subject to the problem of spurious correlations. To comprehensively investigate the faithfulness and reliability of entity typing methods, we first systematically define distinct kinds of model biases that are reflected mainly from spurious correlations. Particularly, we identify six types of existing model biases, including mention-context bias, lexical overlapping bias, named entity bias, pronoun bias, dependency bias, and overgeneralization bias. To mitigate model biases, we then introduce a counterfactual data augmentation method. By augmenting the original training set with their debiased counterparts, models are forced to fully comprehend sentences and discover the fundamental cues for entity typing, rather than relying on spurious correlations for shortcuts. Experimental results on the UFET dataset show our counterfactual data augmentation approach helps improve generalization of different entity typing models with consistently better performance on both the original and debiased test sets.

Songjun Tu, Jiahao Lin, Xiangyu Tian et al.

Recent advancements in post-training methodologies for large language models (LLMs) have highlighted reinforcement learning (RL) as a critical component for enhancing reasoning. However, the substantial computational costs associated with RL-based approaches have led to growing interest in alternative paradigms, such as Direct Preference Optimization (DPO). In this study, we investigate the effectiveness of DPO in facilitating self-improvement for LLMs through iterative preference-based learning. We demonstrate that a single round of DPO with coarse filtering significantly enhances mathematical reasoning performance, particularly for strong base model. Furthermore, we design an iterative enhancement framework for both the generator and the reward model (RM), enabling their mutual improvement through online interaction across multiple rounds of DPO. Finally, with simple verifiable rewards, our model DPO-VP achieves RL-level performance with significantly lower computational overhead. These findings highlight DPO as a scalable and cost-effective alternative to RL, offering a practical solution for enhancing LLM reasoning in resource-constrained situations.

Qin Liu, Fei Wang, Nan Xu et al.

Performance of large language models (LLMs) may vary with different prompts or instructions of even the same task. One commonly recognized factor for this phenomenon is the model's familiarity with the given prompt or instruction, which is typically estimated by its perplexity. However, finding the prompt with the lowest perplexity is challenging, given the enormous space of possible prompting phrases. In this paper, we propose monotonic paraphrasing (MonoPara), an end-to-end decoding strategy that paraphrases given prompts or instructions into their lower perplexity counterparts based on an ensemble of a paraphrase LM for prompt (or instruction) rewriting, and a target LM (i.e. the prompt or instruction executor) that constrains the generation for lower perplexity. The ensemble decoding process can efficiently paraphrase the original prompt without altering its semantic meaning, while monotonically decreasing the perplexity of each generation as calculated by the target LM. We explore in detail both greedy and search-based decoding as two alternative decoding schemes of MonoPara. Notably, MonoPara does not require any training and can monotonically lower the perplexity of the paraphrased prompt or instruction, leading to improved performance of zero-shot LM prompting as evaluated on a wide selection of tasks. In addition, MonoPara is also shown to effectively improve LMs' generalization on perturbed and unseen task instructions.

Jiahao Zhao, Shuaixing Zhang, Nan Xu et al.

LLM-based automatic survey systems are transforming how users acquire information from the web by integrating retrieval, organization, and content synthesis into end-to-end generation pipelines. While recent works focus on developing new generation pipelines, how to evaluate such complex systems remains a significant challenge. To this end, we introduce SurveyEval, a comprehensive benchmark that evaluates automatically generated surveys across three dimensions: overall quality, outline coherence, and reference accuracy. We extend the evaluation across 7 subjects and augment the LLM-as-a-Judge framework with human references to strengthen evaluation-human alignment. Evaluation results show that while general long-text or paper-writing systems tend to produce lower-quality surveys, specialized survey-generation systems are able to deliver substantially higher-quality results. We envision SurveyEval as a scalable testbed to understand and improve automatic survey systems across diverse subjects and evaluation criteria.

Nan Xu, Hongming Zhang, Jianshu Chen

Existing event-centric NLP models often only apply to the pre-defined ontology, which significantly restricts their generalization capabilities. This paper presents CEO, a novel Corpus-based Event Ontology induction model to relax the restriction imposed by pre-defined event ontologies. Without direct supervision, CEO leverages distant supervision from available summary datasets to detect corpus-wise salient events and exploits external event knowledge to force events within a short distance to have close embeddings. Experiments on three popular event datasets show that the schema induced by CEO has better coverage and higher accuracy than previous methods. Moreover, CEO is the first event ontology induction model that can induce a hierarchical event ontology with meaningful names on eleven open-domain corpora, making the induced schema more trustworthy and easier to be further curated.

Nan Xu, Chunting Zhou, Asli Celikyilmaz et al.

Given a prefix (context), open-ended generation aims to decode texts that are coherent, which do not abruptly drift from previous topics, and informative, which do not suffer from undesired repetitions. In this paper, we propose Look-back, an improved decoding algorithm that leverages the Kullback-Leibler divergence to track the distribution distance between current and historical decoding steps. Thus Look-back can automatically predict potential repetitive phrase and topic drift, and remove tokens that may cause the failure modes, restricting the next token probability distribution within a plausible distance to the history. We perform decoding experiments on document continuation and story generation, and demonstrate that Look-back is able to generate more fluent and coherent text, outperforming other strong decoding methods significantly in both automatic and human evaluations.

Xiangtian Zheng, Nan Xu, Loc Trinh et al.

The electric grid is a key enabling infrastructure for the ambitious transition towards carbon neutrality as we grapple with climate change. With deepening penetration of renewable energy resources and electrified transportation, the reliable and secure operation of the electric grid becomes increasingly challenging. In this paper, we present PSML, a first-of-its-kind open-access multi-scale time-series dataset, to aid in the development of data-driven machine learning (ML) based approaches towards reliable operation of future electric grids. The dataset is generated through a novel transmission + distribution (T+D) co-simulation designed to capture the increasingly important interactions and uncertainties of the grid dynamics, containing electric load, renewable generation, weather, voltage and current measurements over multiple spatio-temporal scales. Using PSML, we provide state-of-the-art ML baselines on three challenging use cases of critical importance to achieve: (i) early detection, accurate classification and localization of dynamic disturbance events; (ii) robust hierarchical forecasting of load and renewable energy with the presence of uncertainties and extreme events; and (iii) realistic synthetic generation of physical-law-constrained measurement time series. We envision that this dataset will enable advances for ML in dynamic systems, while simultaneously allowing ML researchers to contribute towards carbon-neutral electricity and mobility.

Chuizheng Meng, Loc Trinh, Nan Xu et al.

The recent release of large-scale healthcare datasets has greatly propelled the research of data-driven deep learning models for healthcare applications. However, due to the nature of such deep black-boxed models, concerns about interpretability, fairness, and biases in healthcare scenarios where human lives are at stake call for a careful and thorough examinations of both datasets and models. In this work, we focus on MIMIC-IV (Medical Information Mart for Intensive Care, version IV), the largest publicly available healthcare dataset, and conduct comprehensive analyses of dataset representation bias as well as interpretability and prediction fairness of deep learning models for in-hospital mortality prediction. In terms of interpretabilty, we observe that (1) the best performing interpretability method successfully identifies critical features for mortality prediction on various prediction models; (2) demographic features are important for prediction. In terms of fairness, we observe that (1) there exists disparate treatment in prescribing mechanical ventilation among patient groups across ethnicity, gender and age; (2) all of the studied mortality predictors are generally fair while the IMV-LSTM (Interpretable Multi-Variable Long Short-Term Memory) model provides the most accurate and unbiased predictions across all protected groups. We further draw concrete connections between interpretability methods and fairness metrics by showing how feature importance from interpretability methods can be beneficial in quantifying potential disparities in mortality predictors.