Alert button
Picture for Qianli Ma

Qianli Ma

Alert button

Improving Factual Consistency of Text Summarization by Adversarially Decoupling Comprehension and Embellishment Abilities of LLMs

Nov 01, 2023
Huawen Feng, Yan Fan, Xiong Liu, Ting-En Lin, Zekun Yao, Yuchuan Wu, Fei Huang, Yongbin Li, Qianli Ma

Despite the recent progress in text summarization made by large language models (LLMs), they often generate summaries that are factually inconsistent with original articles, known as "hallucinations" in text generation. Unlike previous small models (e.g., BART, T5), current LLMs make fewer silly mistakes but more sophisticated ones, such as imposing cause and effect, adding false details, and overgeneralizing, etc. These hallucinations are challenging to detect through traditional methods, which poses great challenges for improving the factual consistency of text summarization. In this paper, we propose an adversarially DEcoupling method to disentangle the Comprehension and EmbellishmeNT abilities of LLMs (DECENT). Furthermore, we adopt a probing-based parameter-efficient technique to cover the shortage of sensitivity for true and false in the training process of LLMs. In this way, LLMs are less confused about embellishing and understanding, thus can execute the instructions more accurately and have enhanced abilities to distinguish hallucinations. Experimental results show that DECENT significantly improves the reliability of text summarization based on LLMs.

Viaarxiv icon

LoBaSS: Gauging Learnability in Supervised Fine-tuning Data

Oct 16, 2023
Haotian Zhou, Tingkai Liu, Qianli Ma, Jianbo Yuan, Pengfei Liu, Yang You, Hongxia Yang

Figure 1 for LoBaSS: Gauging Learnability in Supervised Fine-tuning Data
Figure 2 for LoBaSS: Gauging Learnability in Supervised Fine-tuning Data
Figure 3 for LoBaSS: Gauging Learnability in Supervised Fine-tuning Data
Figure 4 for LoBaSS: Gauging Learnability in Supervised Fine-tuning Data

Supervised Fine-Tuning (SFT) serves as a crucial phase in aligning Large Language Models (LLMs) to specific task prerequisites. The selection of fine-tuning data profoundly influences the model's performance, whose principle is traditionally grounded in data quality and distribution. In this paper, we introduce a new dimension in SFT data selection: learnability. This new dimension is motivated by the intuition that SFT unlocks capabilities acquired by a LLM during the pretraining phase. Given that different pretrained models have disparate capabilities, the SFT data appropriate for one may not suit another. Thus, we introduce the term learnability to define the suitability of data for effective learning by the model. We present the Loss Based SFT Data Selection (LoBaSS) method, utilizing data learnability as the principal criterion for the selection SFT data. This method provides a nuanced approach, allowing the alignment of data selection with inherent model capabilities, ensuring optimal compatibility and learning efficiency. In experimental comparisons involving 7B and 13B models, our LoBaSS method is able to surpass full-data fine-tuning at merely 6% of the total training data. When employing 16.7% of the data, LoBaSS harmonizes the model's capabilities across conversational and mathematical domains, proving its efficacy and adaptability.

Viaarxiv icon

Let's reward step by step: Step-Level reward model as the Navigators for Reasoning

Oct 16, 2023
Qianli Ma, Haotian Zhou, Tingkai Liu, Jianbo Yuan, Pengfei Liu, Yang You, Hongxia Yang

Figure 1 for Let's reward step by step: Step-Level reward model as the Navigators for Reasoning
Figure 2 for Let's reward step by step: Step-Level reward model as the Navigators for Reasoning
Figure 3 for Let's reward step by step: Step-Level reward model as the Navigators for Reasoning
Figure 4 for Let's reward step by step: Step-Level reward model as the Navigators for Reasoning

Recent years have seen considerable advancements in multi-step reasoning with Large Language Models (LLMs). The previous studies have elucidated the merits of integrating feedback or search mechanisms during model inference to improve the reasoning accuracy. The Process-Supervised Reward Model (PRM), typically furnishes LLMs with step-by-step feedback during the training phase, akin to Proximal Policy Optimization (PPO) or reject sampling. Our objective is to examine the efficacy of PRM in the inference phase to help discern the optimal solution paths for multi-step tasks such as mathematical reasoning and code generation. To this end, we propose a heuristic greedy search algorithm that employs the step-level feedback from PRM to optimize the reasoning pathways explored by LLMs. This tailored PRM demonstrated enhanced results compared to the Chain of Thought (CoT) on mathematical benchmarks like GSM8K and MATH. Additionally, to explore the versatility of our approach, we develop a novel method to automatically generate step-level reward dataset for coding tasks and observed similar improved performance in the code generation tasks. Thus highlighting the robust nature of our reward-model-based approach to inference for reasoning tasks.

Viaarxiv icon

Neural Operator Variational Inference based on Regularized Stein Discrepancy for Deep Gaussian Processes

Sep 22, 2023
Jian Xu, Shian Du, Junmei Yang, Qianli Ma, Delu Zeng

Figure 1 for Neural Operator Variational Inference based on Regularized Stein Discrepancy for Deep Gaussian Processes
Figure 2 for Neural Operator Variational Inference based on Regularized Stein Discrepancy for Deep Gaussian Processes
Figure 3 for Neural Operator Variational Inference based on Regularized Stein Discrepancy for Deep Gaussian Processes
Figure 4 for Neural Operator Variational Inference based on Regularized Stein Discrepancy for Deep Gaussian Processes

Deep Gaussian Process (DGP) models offer a powerful nonparametric approach for Bayesian inference, but exact inference is typically intractable, motivating the use of various approximations. However, existing approaches, such as mean-field Gaussian assumptions, limit the expressiveness and efficacy of DGP models, while stochastic approximation can be computationally expensive. To tackle these challenges, we introduce Neural Operator Variational Inference (NOVI) for Deep Gaussian Processes. NOVI uses a neural generator to obtain a sampler and minimizes the Regularized Stein Discrepancy in L2 space between the generated distribution and true posterior. We solve the minimax problem using Monte Carlo estimation and subsampling stochastic optimization techniques. We demonstrate that the bias introduced by our method can be controlled by multiplying the Fisher divergence with a constant, which leads to robust error control and ensures the stability and precision of the algorithm. Our experiments on datasets ranging from hundreds to tens of thousands demonstrate the effectiveness and the faster convergence rate of the proposed method. We achieve a classification accuracy of 93.56 on the CIFAR10 dataset, outperforming SOTA Gaussian process methods. Furthermore, our method guarantees theoretically controlled prediction error for DGP models and demonstrates remarkable performance on various datasets. We are optimistic that NOVI has the potential to enhance the performance of deep Bayesian nonparametric models and could have significant implications for various practical applications

Viaarxiv icon

Preserving Commonsense Knowledge from Pre-trained Language Models via Causal Inference

Jun 19, 2023
Junhao Zheng, Qianli Ma, Shengjie Qiu, Yue Wu, Peitian Ma, Junlong Liu, Huawen Feng, Xichen Shang, Haibin Chen

Figure 1 for Preserving Commonsense Knowledge from Pre-trained Language Models via Causal Inference
Figure 2 for Preserving Commonsense Knowledge from Pre-trained Language Models via Causal Inference
Figure 3 for Preserving Commonsense Knowledge from Pre-trained Language Models via Causal Inference
Figure 4 for Preserving Commonsense Knowledge from Pre-trained Language Models via Causal Inference

Fine-tuning has been proven to be a simple and effective technique to transfer the learned knowledge of Pre-trained Language Models (PLMs) to downstream tasks. However, vanilla fine-tuning easily overfits the target data and degrades the generalization ability. Most existing studies attribute it to catastrophic forgetting, and they retain the pre-trained knowledge indiscriminately without identifying what knowledge is transferable. Motivated by this, we frame fine-tuning into a causal graph and discover that the crux of catastrophic forgetting lies in the missing causal effects from the pretrained data. Based on the causal view, we propose a unified objective for fine-tuning to retrieve the causality back. Intriguingly, the unified objective can be seen as the sum of the vanilla fine-tuning objective, which learns new knowledge from target data, and the causal objective, which preserves old knowledge from PLMs. Therefore, our method is flexible and can mitigate negative transfer while preserving knowledge. Since endowing models with commonsense is a long-standing challenge, we implement our method on commonsense QA with a proposed heuristic estimation to verify its effectiveness. In the experiments, our method outperforms state-of-the-art fine-tuning methods on all six commonsense QA datasets and can be implemented as a plug-in module to inflate the performance of existing QA models.

* ACL 2023 (oral paper) 
Viaarxiv icon

Perturbation-based Self-supervised Attention for Attention Bias in Text Classification

May 25, 2023
Huawen Feng, Zhenxi Lin, Qianli Ma

Figure 1 for Perturbation-based Self-supervised Attention for Attention Bias in Text Classification
Figure 2 for Perturbation-based Self-supervised Attention for Attention Bias in Text Classification
Figure 3 for Perturbation-based Self-supervised Attention for Attention Bias in Text Classification
Figure 4 for Perturbation-based Self-supervised Attention for Attention Bias in Text Classification

In text classification, the traditional attention mechanisms usually focus too much on frequent words, and need extensive labeled data in order to learn. This paper proposes a perturbation-based self-supervised attention approach to guide attention learning without any annotation overhead. Specifically, we add as much noise as possible to all the words in the sentence without changing their semantics and predictions. We hypothesize that words that tolerate more noise are less significant, and we can use this information to refine the attention distribution. Experimental results on three text classification tasks show that our approach can significantly improve the performance of current attention-based models, and is more effective than existing self-supervised methods. We also provide a visualization analysis to verify the effectiveness of our approach.

Viaarxiv icon

A Survey on Time-Series Pre-Trained Models

May 18, 2023
Qianli Ma, Zhen Liu, Zhenjing Zheng, Ziyang Huang, Siying Zhu, Zhongzhong Yu, James T. Kwok

Figure 1 for A Survey on Time-Series Pre-Trained Models
Figure 2 for A Survey on Time-Series Pre-Trained Models
Figure 3 for A Survey on Time-Series Pre-Trained Models
Figure 4 for A Survey on Time-Series Pre-Trained Models

Time-Series Mining (TSM) is an important research area since it shows great potential in practical applications. Deep learning models that rely on massive labeled data have been utilized for TSM successfully. However, constructing a large-scale well-labeled dataset is difficult due to data annotation costs. Recently, Pre-Trained Models have gradually attracted attention in the time series domain due to their remarkable performance in computer vision and natural language processing. In this survey, we provide a comprehensive review of Time-Series Pre-Trained Models (TS-PTMs), aiming to guide the understanding, applying, and studying TS-PTMs. Specifically, we first briefly introduce the typical deep learning models employed in TSM. Then, we give an overview of TS-PTMs according to the pre-training techniques. The main categories we explore include supervised, unsupervised, and self-supervised TS-PTMs. Further, extensive experiments are conducted to analyze the advantages and disadvantages of transfer learning strategies, Transformer-based models, and representative TS-PTMs. Finally, we point out some potential directions of TS-PTMs for future work.

* Under review in the IEEE Transactions on Knowledge and Data Engineering 
Viaarxiv icon

Probabilistic Human Mesh Recovery in 3D Scenes from Egocentric Views

Apr 12, 2023
Siwei Zhang, Qianli Ma, Yan Zhang, Sadegh Aliakbarian, Darren Cosker, Siyu Tang

Figure 1 for Probabilistic Human Mesh Recovery in 3D Scenes from Egocentric Views
Figure 2 for Probabilistic Human Mesh Recovery in 3D Scenes from Egocentric Views
Figure 3 for Probabilistic Human Mesh Recovery in 3D Scenes from Egocentric Views
Figure 4 for Probabilistic Human Mesh Recovery in 3D Scenes from Egocentric Views

Automatic perception of human behaviors during social interactions is crucial for AR/VR applications, and an essential component is estimation of plausible 3D human pose and shape of our social partners from the egocentric view. One of the biggest challenges of this task is severe body truncation due to close social distances in egocentric scenarios, which brings large pose ambiguities for unseen body parts. To tackle this challenge, we propose a novel scene-conditioned diffusion method to model the body pose distribution. Conditioned on the 3D scene geometry, the diffusion model generates bodies in plausible human-scene interactions, with the sampling guided by a physics-based collision score to further resolve human-scene inter-penetrations. The classifier-free training enables flexible sampling with different conditions and enhanced diversity. A visibility-aware graph convolution model guided by per-joint visibility serves as the diffusion denoiser to incorporate inter-joint dependencies and per-body-part control. Extensive evaluations show that our method generates bodies in plausible interactions with 3D scenes, achieving both superior accuracy for visible joints and diversity for invisible body parts. The code will be available at https://sanweiliti.github.io/egohmr/egohmr.html.

Viaarxiv icon

Dynamic Point Fields

Apr 06, 2023
Sergey Prokudin, Qianli Ma, Maxime Raafat, Julien Valentin, Siyu Tang

Figure 1 for Dynamic Point Fields
Figure 2 for Dynamic Point Fields
Figure 3 for Dynamic Point Fields
Figure 4 for Dynamic Point Fields

Recent years have witnessed significant progress in the field of neural surface reconstruction. While the extensive focus was put on volumetric and implicit approaches, a number of works have shown that explicit graphics primitives such as point clouds can significantly reduce computational complexity, without sacrificing the reconstructed surface quality. However, less emphasis has been put on modeling dynamic surfaces with point primitives. In this work, we present a dynamic point field model that combines the representational benefits of explicit point-based graphics with implicit deformation networks to allow efficient modeling of non-rigid 3D surfaces. Using explicit surface primitives also allows us to easily incorporate well-established constraints such as-isometric-as-possible regularisation. While learning this deformation model is prone to local optima when trained in a fully unsupervised manner, we propose to additionally leverage semantic information such as keypoint dynamics to guide the deformation learning. We demonstrate our model with an example application of creating an expressive animatable human avatar from a collection of 3D scans. Here, previous methods mostly rely on variants of the linear blend skinning paradigm, which fundamentally limits the expressivity of such models when dealing with complex cloth appearances such as long skirts. We show the advantages of our dynamic point field framework in terms of its representational power, learning efficiency, and robustness to out-of-distribution novel poses.

Viaarxiv icon

Pair-Based Joint Encoding with Relational Graph Convolutional Networks for Emotion-Cause Pair Extraction

Dec 04, 2022
Junlong Liu, Xichen Shang, Qianli Ma

Figure 1 for Pair-Based Joint Encoding with Relational Graph Convolutional Networks for Emotion-Cause Pair Extraction
Figure 2 for Pair-Based Joint Encoding with Relational Graph Convolutional Networks for Emotion-Cause Pair Extraction
Figure 3 for Pair-Based Joint Encoding with Relational Graph Convolutional Networks for Emotion-Cause Pair Extraction
Figure 4 for Pair-Based Joint Encoding with Relational Graph Convolutional Networks for Emotion-Cause Pair Extraction

Emotion-cause pair extraction (ECPE) aims to extract emotion clauses and corresponding cause clauses, which have recently received growing attention. Previous methods sequentially encode features with a specified order. They first encode the emotion and cause features for clause extraction and then combine them for pair extraction. This lead to an imbalance in inter-task feature interaction where features extracted later have no direct contact with the former. To address this issue, we propose a novel Pair-Based Joint Encoding (PBJE) network, which generates pairs and clauses features simultaneously in a joint feature encoding manner to model the causal relationship in clauses. PBJE can balance the information flow among emotion clauses, cause clauses and pairs. From a multi-relational perspective, we construct a heterogeneous undirected graph and apply the Relational Graph Convolutional Network (RGCN) to capture the various relationship between clauses and the relationship between pairs and clauses. Experimental results show that PBJE achieves state-of-the-art performance on the Chinese benchmark corpus.

* Accepted to EMNLP 2022 
Viaarxiv icon