Jiawei Zhang


2024

pdf bib
Unveiling the Magic: Investigating Attention Distillation in Retrieval-Augmented Generation
Zizhong Li | Haopeng Zhang | Jiawei Zhang
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)

Retrieval-augmented generation framework addresses the limitations of large language models by enabling real-time knowledge updates for more accurate answers. An efficient way in the training phase of retrieval-augmented models is attention distillation, which uses attention scores as supervision signals instead of manually annotated query-document pairs. Despite its growing popularity, the detailed mechanisms behind the success of attention distillation remain unexplored, particularly the specific patterns it leverages to benefit training. In this paper, we address this gap by conducting a comprehensive investigation of attention distillation workflow and identifying key factors influencing the learning performance of retrieval-augmented language models. We further propose several insightful indicators for optimizing models’ training methods and avoiding ineffective training.

pdf bib
Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphs
Bowen Jin | Chulin Xie | Jiawei Zhang | Kashob Kumar Roy | Yu Zhang | Zheng Li | Ruirui Li | Xianfeng Tang | Suhang Wang | Yu Meng | Jiawei Han
Findings of the Association for Computational Linguistics ACL 2024

Large language models (LLMs), while exhibiting exceptional performance, suffer from hallucinations, especially on knowledge-intensive tasks. Existing works propose to augment LLMs with individual text units retrieved from external knowledge corpora to alleviate the issue. However, in many domains, texts are interconnected (e.g., academic papers in a bibliographic graph are linked by citations and co-authorships) which form a (text-attributed) graph. The knowledge in such graphs is encoded not only in single texts/nodes but also in their associated connections. To facilitate the research of augmenting LLMs with graphs, we manually construct a Graph Reasoning Benchmark dataset called GRBench, containing 1,740 questions that can be answered with the knowledge from 10 domain graphs. Then, we propose a simple and effective framework called Graph Chain-of-thought (Graph-CoT) to augment LLMs with graphs by encouraging LLMs to reason on the graph iteratively. Each Graph-CoT iteration consists of three sub-steps: LLM reasoning, LLM-graph interaction, and graph execution. We conduct systematic experiments with three LLM backbones on GRBench, where Graph-CoT outperforms the baselines consistently. The code is available at https://github.com/PeterGriffinJin/Graph-CoT/.

pdf bib
Beyond Text: Unveiling Multimodal Proficiency of Large Language Models with MultiAPI Benchmark
Xiao Liu | Jianfeng Lin | Jiawei Zhang
Proceedings of the 1st Workshop on Towards Knowledgeable Language Models (KnowLLM 2024)

The proliferation of Large Language Models like ChatGPT has significantly advanced language understanding and generation, impacting a broad spectrum of applications. However, these models predominantly excel in text-based tasks, overlooking the complexity of real-world multimodal information. This study introduces MultiAPI, a pioneering comprehensive large-scale API benchmark dataset aimed at expanding LLMs’ proficiency in multimodal contexts. Developed collaboratively through ChatGPT, MultiAPI consists of 187 diverse API calls and 1,799 contextual prompts, offering a unique platform evaluation of tool-augmented LLMs handling multimodal tasks. Through comprehensive experiments, our findings reveal that while LLMs demonstrate proficiency in API call decision-making, they face challenges in domain identification, function selection, and argument generation. What’s more, we surprisingly notice that auxiliary context can actually impair the performance. An in-depth error analysis paves the way for a new paradigm to address these challenges, suggesting a potential direction for future LLM research.

2023

pdf bib
DiffuSum: Generation Enhanced Extractive Summarization with Diffusion
Haopeng Zhang | Xiao Liu | Jiawei Zhang
Findings of the Association for Computational Linguistics: ACL 2023

Extractive summarization aims to form a summary by directly extracting sentences from the source document. Existing works mostly formulate it as a sequence labeling problem by making individual sentence label predictions. This paper proposes DiffuSum, a novel paradigm for extractive summarization, by directly generating the desired summary sentence representations with diffusion models and extracting sentences based on sentence representation matching. In addition, DiffuSum jointly optimizes a contrastive sentence encoder with a matching loss for sentence representation alignment and a multi-class contrastive loss for representation diversity. Experimental results show that DiffuSum achieves the new state-of-the-art extractive results on CNN/DailyMail with ROUGE scores of 44.83/22.56/40.56. Experiments on the other two datasets with different summary lengths and cross-dataset evaluation also demonstrate the effectiveness of DiffuSum. The strong performance of our framework shows the great potential of adapting generative models for extractive summarization.

pdf bib
Extractive Summarization via ChatGPT for Faithful Summary Generation
Haopeng Zhang | Xiao Liu | Jiawei Zhang
Findings of the Association for Computational Linguistics: EMNLP 2023

Extractive summarization is a crucial task in natural language processing that aims to condense long documents into shorter versions by directly extracting sentences. The recent introduction of large language models has attracted significant interest in the NLP community due to its remarkable performance on a wide range of downstream tasks. This paper first presents a thorough evaluation of ChatGPT’s performance on extractive summarization and compares it with traditional fine-tuning methods on various benchmark datasets. Our experimental analysis reveals that ChatGPT exhibits inferior extractive summarization performance in terms of ROUGE scores compared to existing supervised systems, while achieving higher performance based on LLM-based evaluation metrics. In addition, we explore the effectiveness of in-context learning and chain-of-thought reasoning for enhancing its performance. Furthermore, we find that applying an extract-then-generate pipeline with ChatGPT yields significant performance improvements over abstractive baselines in terms of summary faithfulness. These observations highlight potential directions for enhancing ChatGPT’s capabilities in faithful summarization using two-stage approaches.

pdf bib
SummIt: Iterative Text Summarization via ChatGPT
Haopeng Zhang | Xiao Liu | Jiawei Zhang
Findings of the Association for Computational Linguistics: EMNLP 2023

Existing text summarization systems have made significant progress in recent years, but typically generate summaries in a single step. The one-shot summarization setting is sometimes inadequate, however, as the generated summary may contain hallucinations or overlook important details related to the reader’s interests. In this paper, we address this limitation by proposing SummIt, an iterative text summarization framework based on large language models like ChatGPT. Our framework enables the model to refine the generated summary iteratively through self-evaluation and feedback, closely resembling the iterative process humans undertake when drafting and revising summaries. Furthermore, we explore the potential benefits of integrating knowledge and topic extractors into the framework to enhance summary faithfulness and controllability. We evaluate the performance of our framework on three benchmark summarization datasets through empirical and qualitative analyses. We also conduct a human evaluation to validate the effectiveness of the model’s refinements and find a potential issue of over-correction.

pdf bib
Unsupervised Multi-document Summarization with Holistic Inference
Haopeng Zhang | Sangwoo Cho | Kaiqiang Song | Xiaoyang Wang | Hongwei Wang | Jiawei Zhang | Dong Yu
Findings of the Association for Computational Linguistics: IJCNLP-AACL 2023 (Findings)

pdf bib
Contrastive Hierarchical Discourse Graph for Scientific Document Summarization
Haopeng Zhang | Xiao Liu | Jiawei Zhang
Proceedings of the 4th Workshop on Computational Approaches to Discourse (CODI 2023)

The extended structural context has made scientific paper summarization a challenging task. This paper proposes CHANGES, a contrastive hierarchical graph neural network for extractive scientific paper summarization. CHANGES represents a scientific paper with a hierarchical discourse graph and learns effective sentence representations with dedicated designed hierarchical graph information aggregation. We also propose a graph contrastive learning module to learn global theme-aware sentence representations. Extensive experiments on the PubMed and arXiv benchmark datasets prove the effectiveness of CHANGES and the importance of capturing hierarchical structure information in modeling scientific papers.

2022

pdf bib
HEGEL: Hypergraph Transformer for Long Document Summarization
Haopeng Zhang | Xiao Liu | Jiawei Zhang
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Extractive summarization for long documents is challenging due to the extended structured input context. The long-distance sentence dependency hinders cross-sentence relations modeling, the critical step of extractive summarization. This paper proposes HEGEL, a hypergraph neural network for long document summarization by capturing high-order cross-sentence relations. HEGEL updates and learns effective sentence representations with hypergraph transformer layers and fuses different types of sentence dependencies, including latent topics, keywords coreference, and section structure. We validate HEGEL by conducting extensive experiments on two benchmark datasets, and experimental results demonstrate the effectiveness and efficiency of HEGEL.

2020

pdf bib
Text Graph Transformer for Document Classification
Haopeng Zhang | Jiawei Zhang
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Text classification is a fundamental problem in natural language processing. Recent studies applied graph neural network (GNN) techniques to capture global word co-occurrence in a corpus. However, previous works are not scalable to large-sized corpus and ignore the heterogeneity of the text graph. To address these problems, we introduce a novel Transformer based heterogeneous graph neural network, namely Text Graph Transformer (TG-Transformer). Our model learns effective node representations by capturing structure and heterogeneity from the text graph. We propose a mini-batch text graph sampling method that significantly reduces computing and memory costs to handle large-sized corpus. Extensive experiments have been conducted on several benchmark datasets, and the results demonstrate that TG-Transformer outperforms state-of-the-art approaches on text classification task.

2019

pdf bib
Parallax: Visualizing and Understanding the Semantics of Embedding Spaces via Algebraic Formulae
Piero Molino | Yang Wang | Jiawei Zhang
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations

Embeddings are a fundamental component of many modern machine learning and natural language processing models. Understanding them and visualizing them is essential for gathering insights about the information they capture and the behavior of the models. In this paper, we introduce Parallax, a tool explicitly designed for this task. Parallax allows the user to use both state-of-the-art embedding analysis methods (PCA and t-SNE) and a simple yet effective task-oriented approach where users can explicitly define the axes of the projection through algebraic formulae. %consists in projecting them in two-dimensional planes without any interpretable semantics associated to the axes of the projection, which makes detailed analyses and comparison among multiple sets of embeddings challenging. In this approach, embeddings are projected into a semantically meaningful subspace, which enhances interpretability and allows for more fine-grained analysis. We demonstrate the power of the tool and the proposed methodology through a series of case studies and a user study.