Alert button
Picture for Shulin Cao

Shulin Cao

Alert button

Probabilistic Tree-of-thought Reasoning for Answering Knowledge-intensive Complex Questions

Nov 23, 2023
Shulin Cao, Jiajie Zhang, Jiaxin Shi, Xin Lv, Zijun Yao, Qi Tian, Juanzi Li, Lei Hou

Large language models (LLMs) are capable of answering knowledge-intensive complex questions with chain-of-thought (CoT) reasoning. However, they tend to generate factually incorrect reasoning steps when the required knowledge is not available or up-to-date in models' parameters. Recent works turn to retrieving external knowledge to augment CoT reasoning. Despite being promising, these chain-based methods suffer from: 1) Negative retrieval. Unnecessary or incorrect retrieval may mislead the reasoning; 2) Limited sight. Lacking the ability to look backward or forward, a local error in one step will propagate along the chain. In this paper, we propose a novel approach: Probabilistic Tree-of-thought Reasoning (ProbTree). First, LLMs translate a complex question into a query tree, in which each non-root node denotes a sub-question of its parent node. Then, probabilistic reasoning is conducted over the tree, by solving questions from leaf to root considering the confidence of both question decomposing and answering. During reasoning, for leaf nodes, LLMs choose a more confident answer from Closed-book QA that employs parametric knowledge and Open-book QA that employs retrieved external knowledge, thus eliminating the negative retrieval problem. For non-leaf nodes, with the hierarchical structure, LLMs have broader sights and are able to globally reason with the information from child nodes, thus recovering from local errors. The experiments on three Complex QA datasets under the open-domain setting show that our approach outperforms SOTA methods significantly, demonstrating the effect of probabilistic tree-of-thought reasoning.

* Accepted by EMNLP 2023 
Viaarxiv icon

VisKoP: Visual Knowledge oriented Programming for Interactive Knowledge Base Question Answering

Jul 06, 2023
Zijun Yao, Yuanyong Chen, Xin Lv, Shulin Cao, Amy Xin, Jifan Yu, Hailong Jin, Jianjun Xu, Peng Zhang, Lei Hou, Juanzi Li

Figure 1 for VisKoP: Visual Knowledge oriented Programming for Interactive Knowledge Base Question Answering
Figure 2 for VisKoP: Visual Knowledge oriented Programming for Interactive Knowledge Base Question Answering
Figure 3 for VisKoP: Visual Knowledge oriented Programming for Interactive Knowledge Base Question Answering
Figure 4 for VisKoP: Visual Knowledge oriented Programming for Interactive Knowledge Base Question Answering

We present Visual Knowledge oriented Programming platform (VisKoP), a knowledge base question answering (KBQA) system that integrates human into the loop to edit and debug the knowledge base (KB) queries. VisKoP not only provides a neural program induction module, which converts natural language questions into knowledge oriented program language (KoPL), but also maps KoPL programs into graphical elements. KoPL programs can be edited with simple graphical operators, such as dragging to add knowledge operators and slot filling to designate operator arguments. Moreover, VisKoP provides auto-completion for its knowledge base schema and users can easily debug the KoPL program by checking its intermediate results. To facilitate the practical KBQA on a million-entity-level KB, we design a highly efficient KoPL execution engine for the back-end. Experiment results show that VisKoP is highly efficient and user interaction can fix a large portion of wrong KoPL programs to acquire the correct answer. The VisKoP online demo https://demoviskop.xlore.cn (Stable release of this paper) and https://viskop.xlore.cn (Beta release with new features), highly efficient KoPL engine https://pypi.org/project/kopl-engine, and screencast video https://youtu.be/zAbJtxFPTXo are now publicly available.

Viaarxiv icon

KoRC: Knowledge oriented Reading Comprehension Benchmark for Deep Text Understanding

Jul 06, 2023
Zijun Yao, Yantao Liu, Xin Lv, Shulin Cao, Jifan Yu, Lei Hou, Juanzi Li

Figure 1 for KoRC: Knowledge oriented Reading Comprehension Benchmark for Deep Text Understanding
Figure 2 for KoRC: Knowledge oriented Reading Comprehension Benchmark for Deep Text Understanding
Figure 3 for KoRC: Knowledge oriented Reading Comprehension Benchmark for Deep Text Understanding
Figure 4 for KoRC: Knowledge oriented Reading Comprehension Benchmark for Deep Text Understanding

Deep text understanding, which requires the connections between a given document and prior knowledge beyond its text, has been highlighted by many benchmarks in recent years. However, these benchmarks have encountered two major limitations. On the one hand, most of them require human annotation of knowledge, which leads to limited knowledge coverage. On the other hand, they usually use choices or spans in the texts as the answers, which results in narrow answer space. To overcome these limitations, we build a new challenging benchmark named KoRc in this paper. Compared with previous benchmarks, KoRC has two advantages, i.e., broad knowledge coverage and flexible answer format. Specifically, we utilize massive knowledge bases to guide annotators or large language models (LLMs) to construct knowledgable questions. Moreover, we use labels in knowledge bases rather than spans or choices as the final answers. We test state-of-the-art models on KoRC and the experimental results show that the strongest baseline only achieves 68.3% and 30.0% F1 measure in the in-distribution and out-of-distribution test set, respectively. These results indicate that deep text understanding is still an unsolved challenge. The benchmark dataset, leaderboard, and baseline methods are released in https://github.com/THU-KEG/KoRC.

Viaarxiv icon

FC-KBQA: A Fine-to-Coarse Composition Framework for Knowledge Base Question Answering

Jun 26, 2023
Lingxi Zhang, Jing Zhang, Yanling Wang, Shulin Cao, Xinmei Huang, Cuiping Li, Hong Chen, Juanzi Li

Figure 1 for FC-KBQA: A Fine-to-Coarse Composition Framework for Knowledge Base Question Answering
Figure 2 for FC-KBQA: A Fine-to-Coarse Composition Framework for Knowledge Base Question Answering
Figure 3 for FC-KBQA: A Fine-to-Coarse Composition Framework for Knowledge Base Question Answering
Figure 4 for FC-KBQA: A Fine-to-Coarse Composition Framework for Knowledge Base Question Answering

The generalization problem on KBQA has drawn considerable attention. Existing research suffers from the generalization issue brought by the entanglement in the coarse-grained modeling of the logical expression, or inexecutability issues due to the fine-grained modeling of disconnected classes and relations in real KBs. We propose a Fine-to-Coarse Composition framework for KBQA (FC-KBQA) to both ensure the generalization ability and executability of the logical expression. The main idea of FC-KBQA is to extract relevant fine-grained knowledge components from KB and reformulate them into middle-grained knowledge pairs for generating the final logical expressions. FC-KBQA derives new state-of-the-art performance on GrailQA and WebQSP, and runs 4 times faster than the baseline.

Viaarxiv icon

KoLA: Carefully Benchmarking World Knowledge of Large Language Models

Jun 15, 2023
Jifan Yu, Xiaozhi Wang, Shangqing Tu, Shulin Cao, Daniel Zhang-Li, Xin Lv, Hao Peng, Zijun Yao, Xiaohan Zhang, Hanming Li, Chunyang Li, Zheyuan Zhang, Yushi Bai, Yantao Liu, Amy Xin, Nianyi Lin, Kaifeng Yun, Linlu Gong, Jianhui Chen, Zhili Wu, Yunjia Qi, Weikai Li, Yong Guan, Kaisheng Zeng, Ji Qi, Hailong Jin, Jinxin Liu, Yu Gu, Yuan Yao, Ning Ding, Lei Hou, Zhiyuan Liu, Bin Xu, Jie Tang, Juanzi Li

Figure 1 for KoLA: Carefully Benchmarking World Knowledge of Large Language Models
Figure 2 for KoLA: Carefully Benchmarking World Knowledge of Large Language Models
Figure 3 for KoLA: Carefully Benchmarking World Knowledge of Large Language Models
Figure 4 for KoLA: Carefully Benchmarking World Knowledge of Large Language Models

The unprecedented performance of large language models (LLMs) necessitates improvements in evaluations. Rather than merely exploring the breadth of LLM abilities, we believe meticulous and thoughtful designs are essential to thorough, unbiased, and applicable evaluations. Given the importance of world knowledge to LLMs, we construct a Knowledge-oriented LLM Assessment benchmark (KoLA), in which we carefully design three crucial factors: (1) For ability modeling, we mimic human cognition to form a four-level taxonomy of knowledge-related abilities, covering $19$ tasks. (2) For data, to ensure fair comparisons, we use both Wikipedia, a corpus prevalently pre-trained by LLMs, along with continuously collected emerging corpora, aiming to evaluate the capacity to handle unseen data and evolving knowledge. (3) For evaluation criteria, we adopt a contrastive system, including overall standard scores for better numerical comparability across tasks and models and a unique self-contrast metric for automatically evaluating knowledge hallucination. We evaluate $21$ open-source and commercial LLMs and obtain some intriguing findings. The KoLA dataset and open-participation leaderboard are publicly released at https://kola.xlore.cn and will be continuously updated to provide references for developing LLMs and knowledge-related systems.

Viaarxiv icon

Reasoning over Hierarchical Question Decomposition Tree for Explainable Question Answering

May 24, 2023
Jiajie Zhang, Shulin Cao, Tingjia Zhang, Xin Lv, Jiaxin Shi, Qi Tian, Juanzi Li, Lei Hou

Figure 1 for Reasoning over Hierarchical Question Decomposition Tree for Explainable Question Answering
Figure 2 for Reasoning over Hierarchical Question Decomposition Tree for Explainable Question Answering
Figure 3 for Reasoning over Hierarchical Question Decomposition Tree for Explainable Question Answering
Figure 4 for Reasoning over Hierarchical Question Decomposition Tree for Explainable Question Answering

Explainable question answering (XQA) aims to answer a given question and provide an explanation why the answer is selected. Existing XQA methods focus on reasoning on a single knowledge source, e.g., structured knowledge bases, unstructured corpora, etc. However, integrating information from heterogeneous knowledge sources is essential to answer complex questions. In this paper, we propose to leverage question decomposing for heterogeneous knowledge integration, by breaking down a complex question into simpler ones, and selecting the appropriate knowledge source for each sub-question. To facilitate reasoning, we propose a novel two-stage XQA framework, Reasoning over Hierarchical Question Decomposition Tree (RoHT). First, we build the Hierarchical Question Decomposition Tree (HQDT) to understand the semantics of a complex question; then, we conduct probabilistic reasoning over HQDT from root to leaves recursively, to aggregate heterogeneous knowledge at different tree levels and search for a best solution considering the decomposing and answering probabilities. The experiments on complex QA datasets KQA Pro and Musique show that our framework outperforms SOTA methods significantly, demonstrating the effectiveness of leveraging question decomposing for knowledge integration and our RoHT framework.

* has been accepted by ACL2023 
Viaarxiv icon

GraphQ IR: Unifying Semantic Parsing of Graph Query Language with Intermediate Representation

May 24, 2022
Lunyiu Nie, Shulin Cao, Jiaxin Shi, Qi Tian, Lei Hou, Juanzi Li, Jidong Zhai

Figure 1 for GraphQ IR: Unifying Semantic Parsing of Graph Query Language with Intermediate Representation
Figure 2 for GraphQ IR: Unifying Semantic Parsing of Graph Query Language with Intermediate Representation
Figure 3 for GraphQ IR: Unifying Semantic Parsing of Graph Query Language with Intermediate Representation
Figure 4 for GraphQ IR: Unifying Semantic Parsing of Graph Query Language with Intermediate Representation

Subject to the semantic gap lying between natural and formal language, neural semantic parsing is typically bottlenecked by the paucity and imbalance of data. In this paper, we propose a unified intermediate representation (IR) for graph query languages, namely GraphQ IR. With the IR's natural-language-like representation that bridges the semantic gap and its formally defined syntax that maintains the graph structure, neural semantic parser can more effectively convert user queries into our GraphQ IR, which can be later automatically compiled into different downstream graph query languages. Extensive experiments show that our approach can consistently achieve state-of-the-art performance on benchmarks KQA Pro, Overnight and MetaQA. Evaluations under compositional generalization and few-shot learning settings also validate the promising generalization ability of GraphQ IR with at most 11% accuracy improvement.

Viaarxiv icon

A Roadmap for Big Model

Apr 02, 2022
Sha Yuan, Hanyu Zhao, Shuai Zhao, Jiahong Leng, Yangxiao Liang, Xiaozhi Wang, Jifan Yu, Xin Lv, Zhou Shao, Jiaao He, Yankai Lin, Xu Han, Zhenghao Liu, Ning Ding, Yongming Rao, Yizhao Gao, Liang Zhang, Ming Ding, Cong Fang, Yisen Wang, Mingsheng Long, Jing Zhang, Yinpeng Dong, Tianyu Pang, Peng Cui, Lingxiao Huang, Zheng Liang, Huawei Shen, Hui Zhang, Quanshi Zhang, Qingxiu Dong, Zhixing Tan, Mingxuan Wang, Shuo Wang, Long Zhou, Haoran Li, Junwei Bao, Yingwei Pan, Weinan Zhang, Zhou Yu, Rui Yan, Chence Shi, Minghao Xu, Zuobai Zhang, Guoqiang Wang, Xiang Pan, Mengjie Li, Xiaoyu Chu, Zijun Yao, Fangwei Zhu, Shulin Cao, Weicheng Xue, Zixuan Ma, Zhengyan Zhang, Shengding Hu, Yujia Qin, Chaojun Xiao, Zheni Zeng, Ganqu Cui, Weize Chen, Weilin Zhao, Yuan Yao, Peng Li, Wenzhao Zheng, Wenliang Zhao, Ziyi Wang, Borui Zhang, Nanyi Fei, Anwen Hu, Zenan Ling, Haoyang Li, Boxi Cao, Xianpei Han, Weidong Zhan, Baobao Chang, Hao Sun, Jiawen Deng, Chujie Zheng, Juanzi Li, Lei Hou, Xigang Cao, Jidong Zhai, Zhiyuan Liu, Maosong Sun, Jiwen Lu, Zhiwu Lu, Qin Jin, Ruihua Song, Ji-Rong Wen, Zhouchen Lin, Liwei Wang, Hang Su, Jun Zhu, Zhifang Sui, Jiajun Zhang, Yang Liu, Xiaodong He, Minlie Huang, Jian Tang, Jie Tang

Figure 1 for A Roadmap for Big Model
Figure 2 for A Roadmap for Big Model
Figure 3 for A Roadmap for Big Model
Figure 4 for A Roadmap for Big Model

With the rapid development of deep learning, training Big Models (BMs) for multiple downstream tasks becomes a popular paradigm. Researchers have achieved various outcomes in the construction of BMs and the BM application in many fields. At present, there is a lack of research work that sorts out the overall progress of BMs and guides the follow-up research. In this paper, we cover not only the BM technologies themselves but also the prerequisites for BM training and applications with BMs, dividing the BM review into four parts: Resource, Models, Key Technologies and Application. We introduce 16 specific BM-related topics in those four parts, they are Data, Knowledge, Computing System, Parallel Training System, Language Model, Vision Model, Multi-modal Model, Theory&Interpretability, Commonsense Reasoning, Reliability&Security, Governance, Evaluation, Machine Translation, Text Generation, Dialogue and Protein Research. In each topic, we summarize clearly the current studies and propose some future research directions. At the end of this paper, we conclude the further development of BMs in a more general view.

* arXiv admin note: text overlap with arXiv:2107.06499 by other authors 
Viaarxiv icon

Schema-Free Dependency Parsing via Sequence Generation

Jan 28, 2022
Boda Lin, Zijun Yao, Jiaxin Shi, Shulin Cao, Binghao Tang, Si Li, Yong Luo, Juanzi Li, Lei Hou

Figure 1 for Schema-Free Dependency Parsing via Sequence Generation
Figure 2 for Schema-Free Dependency Parsing via Sequence Generation
Figure 3 for Schema-Free Dependency Parsing via Sequence Generation
Figure 4 for Schema-Free Dependency Parsing via Sequence Generation

Dependency parsing aims to extract syntactic dependency structure or semantic dependency structure for sentences. Existing methods suffer the drawbacks of lacking universality or highly relying on the auxiliary decoder. To remedy these drawbacks, we propose to achieve universal and schema-free Dependency Parsing (DP) via Sequence Generation (SG) DPSG by utilizing only the pre-trained language model (PLM) without any auxiliary structures or parsing algorithms. We first explore different serialization designing strategies for converting parsing structures into sequences. Then we design dependency units and concatenate these units into the sequence for DPSG. Thanks to the high flexibility of the sequence generation, our DPSG can achieve both syntactic DP and semantic DP using a single model. By concatenating the prefix to indicate the specific schema with the sequence, our DPSG can even accomplish multi-schemata parsing. The effectiveness of our DPSG is demonstrated by the experiments on widely used DP benchmarks, i.e., PTB, CODT, SDP15, and SemEval16. DPSG achieves comparable results with the first-tier methods on all the benchmarks and even the state-of-the-art (SOTA) performance in CODT and SemEval16. This paper demonstrates our DPSG has the potential to be a new parsing paradigm. We will release our codes upon acceptance.

Viaarxiv icon

Program Transfer and Ontology Awareness for Semantic Parsing in KBQA

Oct 13, 2021
Shulin Cao, Jiaxin Shi, Zijun Yao, Lei Hou, Juanzi Li, Jinghui Xiao

Figure 1 for Program Transfer and Ontology Awareness for Semantic Parsing in KBQA
Figure 2 for Program Transfer and Ontology Awareness for Semantic Parsing in KBQA
Figure 3 for Program Transfer and Ontology Awareness for Semantic Parsing in KBQA
Figure 4 for Program Transfer and Ontology Awareness for Semantic Parsing in KBQA

Semantic parsing in KBQA aims to parse natural language questions into logical forms, whose execution against a knowledge base produces answers. Learning semantic parsers from question-answer pairs requires searching over a huge space of logical forms for ones consistent with answers. Current methods utilize various prior knowlege or entity-level KB constraints to reduce the search space. In this paper, we investigate for the first time prior knowledge from external logical form annotations and ontology-level constraints. We design a hierarchical architecture for program transfer, and propose an ontology-guided pruning algorithm to reduce the search space. The experiments on ComplexWebQuestions show that our method improves the state-of-the-art F1 score from 44.0% to 58.7%, with an absolute gain of 14.7%, which demonstrates the effectiveness of program transfer and ontology awareness.

Viaarxiv icon