No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Improving Complex Reasoning over Knowledge Graph with Logic-Aware Curriculum Tuning
Abstract
Answering complex queries over incomplete knowledge graphs (KGs) is a challenging job. Most previous works have focused on learning entity/relation embeddings and simulating first-order logic operators with various neural networks. However, they are bottlenecked by the inability to share world knowledge to improve logical reasoning, thus resulting in suboptimal performance. In this paper, we propose a complex reasoning schema over KG upon large language models (LLMs), containing a curriculum-based logical-aware instruction tuning framework, named LACT. Specifically, we augment the arbitrary first-order logical queries via binary tree decomposition, to stimulate the reasoning capability of LLMs. To address the difficulty gap among different types of complex queries, we design a simple and flexible logic-aware curriculum learning framework. Experiments across widely used datasets demonstrate that LACT has substantial improvements~(brings an average +5.5% MRR score) over advanced methods, achieving the new state-of-the-art.
ResearchGate has not been able to resolve any citations for this publication.
This paper presents an exhaustive quantitative and qualitative evaluation of Large Language Models (LLMs) for Knowledge Graph (KG) construction and reasoning. We engage in experiments across eight diverse datasets, focusing on four representative tasks encompassing entity and relation extraction, event extraction, link prediction, and question-answering, thereby thoroughly exploring LLMs’ performance in the domain of construction and inference. Empirically, our findings suggest that LLMs, represented by GPT-4, are more suited as inference assistants rather than few-shot information extractors. Specifically, while GPT-4 exhibits good performance in tasks related to KG construction, it excels further in reasoning tasks, surpassing fine-tuned models in certain cases. Moreover, our investigation extends to the potential generalization ability of LLMs for information extraction, leading to the proposition of a Virtual Knowledge Extraction task and the development of the corresponding VINE dataset. Based on these empirical findings, we further propose AutoKG, a multi-agent-based approach employing LLMs and external sources for KG construction and reasoning. We anticipate that this research can provide invaluable insights for future undertakings in the field of knowledge graphs.
Self-attention networks (SAN) have achieved promising performance in a variety of NLP tasks, e.g. neural machine translation (NMT), as they can directly build dependencies among words. But it is weaker at learning positional information than recurrent neural networks (RNN). Natural questions arise: (1) Can we design a component with RNN by directly guiding the syntax dependencies for it? (2) Whether such syntax enhanced sequence modeling component benefits existing NMT structures, e.g. RNN-based NMT and Transformer-based NMT. To answer above question, we propose a simple yet effective recurrent graph syntax encoder, dubbed RGSE, to utilize off-the-shelf syntax dependencies and its intrinsic recurrence property, such that RGSE models syntactic dependencies and sequential information (i.e. word order) simultaneously. Experimental studies on various neural machine translation tasks demonstrate that RGSE equipped RNN and Transformer models could gain consistent significant improvements over several strong syntax-aware benchmarks, with minuscule parameters increases. The extensive analysis further illustrates that RGSE does improve the syntactic and semantic preservation ability than SAN, additionally, shows superior robustness to defend syntactic noise than existing syntax-aware NMT models.
Neural link predictors are useful for identifying missing edges in large scale Knowledge Graphs. However, it is still not clear how to use these models for answering more complex queries containing logical conjunctions (∧), disjunctions (∨), and existential quantifiers (∃). We propose a framework for efficiently answering complex queries on in- complete Knowledge Graphs. We translate each query into an end-to-end differentiable objective, where the truth value of each atom is computed by a pre-trained neural link predictor. We then analyse two solutions to the optimisation problem, including gradient-based and combinatorial search. In our experiments, the proposed approach produces more accurate results than state-of-the-art methods — black-box models trained on millions of generated queries — without the need for training on a large and diverse set of complex queries. Using orders of magnitude less training data, we obtain relative improvements ranging from 8% up to 40% in Hits@3 across multiple knowledge graphs. We find that it is possible to explain the outcome of our model in terms of the intermediate solutions identified for each of the complex query atoms. All our source code and datasets are available online (https://github.com/uclnlp/cqd).
Knowledge Graphs (KGs) are ubiquitous structures for information storagein several real-world applications such as web search, e-commerce, social networks, and biology. Querying KGs remains a foundational and challenging problem due to their size and complexity. Promising approaches to tackle this problem include embedding the KG units (e.g., entities and relations) in a Euclidean space such that the query embedding contains the information relevant to its results. These approaches, however, fail to capture the hierarchical nature and semantic information of the entities present in the graph. Additionally, most of these approaches only utilize multi-hop queries (that can be modeled by simple translation operations) to learn embeddings and ignore more complex operations such as intersection and union of simpler queries. To tackle such complex operations, in this paper, we formulate KG representation learning as a self-supervised logical query reasoning problem that utilizes translation, intersection and union queries over KGs. We propose Hyperboloid Embeddings (HypE), a novel self-supervised dynamic reasoning framework, that utilizes positive first-order existential queries on a KG to learn representations of its entities and relations as hyperboloids in a Poincaré ball. HypE models the positive first-order queries as geometrical translation, intersection, and union. For the problem of KG reasoning in real-world datasets, the proposed HypE model significantly outperforms the state-of-the art results. We also apply HypE to an anomaly detection task on a popular e-commerce website product taxonomy as well as hierarchically organized web articles and demonstrate significant performance improvements compared to existing baseline methods. Finally, we also visualize the learned HypE embeddings in a Poincaré ball to clearly interpret and comprehend the representation space.
Large language models (LLMs), such as ChatGPT and GPT4, are making new waves in the field of natural language processing and artificial intelligence, due to their emergent ability and generalizability. However, LLMs are black-box models, which often fall short of capturing and accessing factual knowledge. In contrast, Knowledge Graphs (KGs), Wikipedia and Huapu for example, are structured knowledge models that explicitly store rich factual knowledge. KGs can enhance LLMs by providing external knowledge for inference and interpretability. Meanwhile, KGs are difficult to construct and evolve by nature, which challenges the existing methods in KGs to generate new facts and represent unseen knowledge. Therefore, it is complementary to unify LLMs and KGs together and simultaneously leverage their advantages. In this article, we present a forward-looking roadmap for the unification of LLMs and KGs. Our roadmap consists of three general frameworks, namely,
1) KG-enhanced LLMs,
which incorporate KGs during the pre-training and inference phases of LLMs, or for the purpose of enhancing understanding of the knowledge learned by LLMs;
2) LLM-augmented KGs,
that leverage LLMs for different KG tasks such as embedding, completion, construction, graph-to-text generation, and question answering; and
3) Synergized LLMs + KGs
, in which LLMs and KGs play equal roles and work in a mutually beneficial way to enhance both LLMs and KGs for bidirectional reasoning driven by both data and knowledge. We review and summarize existing efforts within these three frameworks in our roadmap and pinpoint their future research directions.
The task of entity alignment between knowledge graphs (KGs) aims to identify every pair of entities from two different KGs that represent the same entity. Many machine learning-based methods have been proposed for this task. However, to our best knowledge, existing methods all require
manually crafted
seed alignments, which are expensive to obtain. In this paper, we propose the first fully automatic alignment method named AutoAlign, which does not require any manually crafted seed alignments. Specifically, for predicate embeddings, AutoAlign constructs a predicate-proximity-graph with the help of large language models to automatically capture the similarity between predicates across two KGs. For entity embeddings, AutoAlign first computes the entity embeddings of each KG independently using TransE, and then shifts the two KGs' entity embeddings into the same vector space by computing the similarity between entities based on their attributes. Thus, both predicate alignment and entity alignment can be done without manually crafted seed alignments. AutoAlign is not only fully automatic, but also highly effective. Experiments using real-world KGs show that AutoAlign improves the performance of entity alignment significantly compared to state-of-the-art methods. Our source code is available at ruizhang-ai/AutoAlign.
Recent pre-trained language models (PLMs) equipped with foundation reasoning skills have shown remarkable performance on downstream complex tasks. However, the significant structure reasoning skill has been rarely studied, which involves modeling implicit structure information within the text and performing explicit logical reasoning over them to deduce the conclusion. This paper proposes a unified learning framework that combines explicit structure reasoning and language pre-training to endow PLMs with the structure reasoning skill. It first identifies several elementary structures within contexts to construct structured queries and performs step-by-step reasoning along the queries to identify the answer entity. The fusion of textual semantics and structure reasoning is achieved by using contextual representations learned by PLMs to initialize the representation space of structures, and performing stepwise reasoning on this semantic representation space. Experimental results on four datasets demonstrate that the proposed model achieves significant improvements in complex reasoning tasks involving diverse structures, and shows transferability to downstream tasks with limited training data and effectiveness for complex reasoning of KGs modality.
The goal of aspect-based sentiment analysis (ABSA) is to determine the sentiment polarity towards an aspect. Because of the expensive and limited amounts of labelled data, the pretraining strategy has become the de facto standard for ABSA. However, there always exists a severe domain shift between the pretraining and downstream ABSA datasets, which hinders effective knowledge transfer when directly fine-tuning, making the downstream task suboptimal. To mitigate this domain shift, we introduce a unified alignment pretraining framework into the vanilla pretrain-finetune pipeline, that has both instance- and knowledge-level alignments. Specifically, we first devise a novel coarse-to-fine retrieval sampling approach to select target domain-related instances from the large-scale pretraining dataset, thus aligning the instances between pretraining and the target domains (
First Stage
). Then, we introduce a knowledge guidance-based strategy to further bridge the domain gap at the knowledge level. In practice, we formulate the model pretrained on the sampled instances into a knowledge guidance model and a learner model. On the target dataset, we design an on-the-fly teacher-student joint fine-tuning approach to progressively transfer the knowledge from the knowledge guidance model to the learner model (
Second Stage
). Therefore, the learner model can maintain more domain-invariant knowledge when learning new knowledge from the target dataset. In the
Third Stage,
the learner model is finetuned to better adapt its learned knowledge to the target dataset. Extensive experiments and analyses on several ABSA benchmarks demonstrate the effectiveness and universality of our proposed pretraining framework.
Aspect-based sentiment analysis (ABSA) is a fine-grained task of sentiment analysis. To better comprehend long complicated sentences and obtain accurate aspect-specific information, linguistic and commonsense knowledge are generally required in this task. However, most current methods employ complicated and inefficient approaches to incorporate external knowledge,
e.g.
, directly searching the graph nodes. Additionally, the complementarity between external knowledge and linguistic information has not been thoroughly studied. To this end, we propose a knowledge graph augmented network (
KGAN
), which aims to effectively incorporate external knowledge with explicitly syntactic and contextual information. In particular, KGAN captures the sentiment feature representations from multiple different perspectives,
i.e.
, context-, syntax- and knowledge-based. First, KGAN learns the contextual and syntactic representations in parallel to fully extract the semantic features. Then, KGAN integrates the knowledge graphs into the embedding space, based on which the aspect-specific knowledge representations are further obtained via an attention mechanism. Last, we propose a hierarchical fusion module to complement these multi-view representations in a
local-to-global
manner. Extensive experiments on five popular ABSA benchmarks demonstrate the effectiveness and robustness of our KGAN. Notably, with the help of the pretrained model of RoBERTa, KGAN achieves a new record of state-of-the-art performance among all datasets.
We consider the problem of embedding entities and relationships of multi relational data in low-dimensional vector spaces. Our objective is to propose a canonical model which is easy to train, contains a reduced number of parameters and can scale up to very large databases. Hence, we propose TransE, a method which models relationships by interpreting them as translations operating on the low-dimensional embeddings of the entities. Despite its simplicity, this assumption proves to be powerful since extensive experiments show that TransE significantly outperforms state-of-the-art methods in link prediction on two knowledge bases. Besides, it can be successfully trained on a large scale data set with 1M entities, 25k relationships and more than 17M training samples.
Humans and animals can perform much more complex tasks than they can acquire using pure trial and error learning. This gap is filled by teaching. One important method of instruction is shaping, in which a teacher decomposes a complete task into sub-components, thereby providing an easier path to learning. Despite its importance, shaping has not been substantially studied in the context of computational modeling of cognitive learning. Here we study the shaping of a hierarchical working memory task using an abstract neural network model as the target learner. Shaping significantly boosts the speed of acquisition of the task compared with conventional training, to a degree that increases with the temporal complexity of the task. Further, it leads to internal representations that are more robust to task manipulations such as reversals. We use the model to investigate some of the elements of successful shaping.
- J Achiam
- S Adler
- S Agarwal
- L Ahmad
- I Akkaya
- F L Aleman
- D Almeida
- J Altenschmidt
- S Altman
- S Anadkat
Achiam, J.; Adler, S.; Agarwal, S.; Ahmad, L.; Akkaya, I.;
Aleman, F. L.; Almeida, D.; Altenschmidt, J.; Altman, S.;
Anadkat, S.; et al. 2023. GPT-4 technical report. arXiv
preprint arXiv:2303.08774.
Adapting neural link predictors for dataefficient complex query answering
- E Arakelyan
- P Minervini
- D Daza
- M Cochez
- I Augenstein
Arakelyan, E.; Minervini, P.; Daza, D.; Cochez, M.; and Augenstein, I. 2024. Adapting neural link predictors for dataefficient complex query answering. In Advances in Neural
Information Processing Systems.
Answering complex logical queries on knowledge graphs via query computation tree optimization
- Y Bai
- X Lv
- J Li
- L Hou
Bai, Y.; Lv, X.; Li, J.; and Hou, L. 2023. Answering complex
logical queries on knowledge graphs via query computation
tree optimization. In International Conference on Machine
Learning.
Modeling heterogeneous hierarchies with relation-specific hyperbolic cones
- Y Bai
- Z Ying
- H Ren
- J Leskovec
Bai, Y.; Ying, Z.; Ren, H.; and Leskovec, J. 2021. Modeling
heterogeneous hierarchies with relation-specific hyperbolic
cones. In Advances in Neural Information Processing Systems.
Fuzzy logic based logical query answering on knowledge graphs
- X Chen
- Z Hu
- Y Sun
Chen, X.; Hu, Z.; and Sun, Y. 2022. Fuzzy logic based logical query answering on knowledge graphs. In the AAAI
Conference on Artificial Intelligence.
Complex Logical Reasoning over Knowledge Graphs using Large Language Models
- N Choudhary
- C K Reddy
Choudhary, N.; and Reddy, C. K. 2023. Complex Logical
Reasoning over Knowledge Graphs using Large Language
Models. arXiv preprint arXiv:2305.01157.
Traversing Knowledge Graphs in Vector Space
- K Guu
- J Miller
- P Liang
Guu, K.; Miller, J.; and Liang, P. 2015. Traversing Knowledge Graphs in Vector Space. In Proceedings of the 2015
Conference on Empirical Methods in Natural Language
Processing.
Embedding logical queries on knowledge graphs
- W Hamilton
- P Bajaj
- M Zitnik
- D Jurafsky
- J Leskovec
Hamilton, W.; Bajaj, P.; Zitnik, M.; Jurafsky, D.; and
Leskovec, J. 2018. Embedding logical queries on knowledge graphs. In Advances in neural information processing
systems.
Logic Query of Thoughts: Guiding Large Language Models to Answer Complex Logic Queries with Knowledge Graphs
- L Liu
- Z Wang
- R Qiu
- Y Ban
- H Tong
Liu, L.; Wang, Z.; Qiu, R.; Ban, Y.; and Tong, H. 2024a.
Logic Query of Thoughts: Guiding Large Language Models
to Answer Complex Logic Queries with Knowledge Graphs.
arXiv preprint arXiv:2404.04264.
Let's Learn Step by Step: Enhancing In-Context Learning Ability with Curriculum Learning
- Y Liu
- J Liu
- X Shi
- Q Cheng
- W Lu
Liu, Y.; Liu, J.; Shi, X.; Cheng, Q.; and Lu, W. 2024b.
Let's Learn Step by Step: Enhancing In-Context Learning Ability with Curriculum Learning. arXiv preprint
arXiv:2402.10738.
Error analysis prompting enables human-like translation evaluation in large language models: A case study on chatgpt
- Q Lu
- B Qiu
- L Ding
- L Xie
- D Tao
Lu, Q.; Qiu, B.; Ding, L.; Xie, L.; and Tao, D. 2023. Error
analysis prompting enables human-like translation evaluation in large language models: A case study on chatgpt. In
Findings of the Association for Computational Linguistics:
ACL-IJCNLP 2024.
- L Luo
- J Ju
- B Xiong
- Y.-F Li
- G Haffari
- S Pan
Luo, L.; Ju, J.; Xiong, B.; Li, Y.-F.; Haffari, G.; and Pan, S.
2023. Chatrule: Mining logical rules with large language
models for knowledge graph reasoning. arXiv preprint
arXiv:2309.01538.
Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning
- L Luo
- Y.-F Li
- G Haffari
- S Pan
Luo, L.; Li, Y.-F.; Haffari, G.; and Pan, S. 2024. Reasoning on Graphs: Faithful and Interpretable Large Language
Model Reasoning. In International Conference on Learning
Representations.
Training language models to follow instructions with human feedback
- L Ouyang
- J Wu
- X Jiang
- D Almeida
- C Wainwright
- P Mishkin
- C Zhang
- S Agarwal
- K Slama
- A Ray
Ouyang, L.; Wu, J.; Jiang, X.; Almeida, D.; Wainwright, C.;
Mishkin, P.; Zhang, C.; Agarwal, S.; Slama, K.; Ray, A.;
et al. 2022. Training language models to follow instructions
with human feedback. In Advances in Neural Information
Processing Systems.
Query2box: Reasoning over Knowledge Graphs in Vector Space Using Box Embeddings
- H Ren
- W Hu
- J Leskovec
Ren, H.; Hu, W.; and Leskovec, J. 2019. Query2box: Reasoning over Knowledge Graphs in Vector Space Using Box
Embeddings. In International Conference on Learning Representations.
Beta embeddings for multihop logical reasoning in knowledge graphs
- H Ren
- J Leskovec
Ren, H.; and Leskovec, J. 2020. Beta embeddings for multihop logical reasoning in knowledge graphs. In Advances in
Neural Information Processing Systems.
- H Touvron
- T Lavril
- G Izacard
- X Martinet
- M.-A Lachaux
- T Lacroix
- B Rozière
- N Goyal
- E Hambro
- F Azhar
Touvron, H.; Lavril, T.; Izacard, G.; Martinet, X.; Lachaux,
M.-A.; Lacroix, T.; Rozière, B.; Goyal, N.; Hambro, E.;
Azhar, F.; et al. 2023a. Llama: Open and efficient foundation
language models. arXiv preprint arXiv:2302.13971.
Llama 2: Open foundation and fine-tuned chat models
- H Touvron
- L Martin
- K Stone
- P Albert
- A Almahairi
- Y Babaei
- N Bashlykov
- S Batra
- P Bhargava
- S Bhosale
Touvron, H.; Martin, L.; Stone, K.; Albert, P.; Almahairi, A.;
Babaei, Y.; Bashlykov, N.; Batra, S.; Bhargava, P.; Bhosale,
S.; et al. 2023b. Llama 2: Open foundation and fine-tuned
chat models. arXiv preprint arXiv:2307.09288.
Knowledge-tuning Large Language Models with Structured Medical Knowledge Bases for Reliable Response Generation in Chinese
- H Wang
- S Zhao
- Z Qiang
- Z Li
- N Xi
- Y Du
- M Cai
- H Guo
- Y Chen
- H Xu
Wang, H.; Zhao, S.; Qiang, Z.; Li, Z.; Xi, N.; Du, Y.; Cai, M.;
Guo, H.; Chen, Y.; Xu, H.; et al. 2023a. Knowledge-tuning
Large Language Models with Structured Medical Knowledge Bases for Reliable Response Generation in Chinese.
arXiv preprint arXiv:2309.04175.
- S Wang
- Z Wei
- M Han
- Z Fan
- H Shan
- Q Zhang
- X Huang
Wang, S.; Wei, Z.; Han, M.; Fan, Z.; Shan, H.; Zhang, Q.;
and Huang, X. 2023b. Query Structure Modeling for Inductive Logical Reasoning Over Knowledge Graphs. arXiv
preprint arXiv:2305.13585.
Aligning large language models with human: A survey
- Y Wang
- W Zhong
- L Li
- F Mi
- X Zeng
- W Huang
- L Shang
- X Jiang
- Q Liu
Wang, Y.; Zhong, W.; Li, L.; Mi, F.; Zeng, X.; Huang, W.;
Shang, L.; Jiang, X.; and Liu, Q. 2023e. Aligning large
language models with human: A survey. arXiv preprint
arXiv:2307.12966.
- Z Wang
- Y Song
- G Y Wong
- S See
Wang, Z.; Song, Y.; Wong, G. Y.; and See, S. 2023f. Logical
message passing networks with one-hop inference on atomic
formulas. arXiv preprint arXiv:2301.08859.
Chain-of-thought prompting elicits reasoning in large language models
- J Wei
- X Wang
- D Schuurmans
- M Bosma
- F Xia
- E Chi
- Q V Le
- D Zhou
Wei, J.; Wang, X.; Schuurmans, D.; Bosma, M.; Xia, F.;
Chi, E.; Le, Q. V.; Zhou, D.; et al. 2022. Chain-of-thought
prompting elicits reasoning in large language models. In
Advances in Neural Information Processing Systems.
- H Yin
- Z Wang
- Y Song
Yin, H.; Wang, Z.; and Song, Y. 2023. Rethinking Complex
Queries on Knowledge Graphs with Neural Link Predictors.
arXiv preprint arXiv:2304.07063.
- A Zeng
- X Liu
- Z Du
- Z Wang
- H Lai
- M Ding
- Z Yang
- Y Xu
- W Zheng
- X Xia
Zeng, A.; Liu, X.; Du, Z.; Wang, Z.; Lai, H.; Ding, M.;
Yang, Z.; Xu, Y.; Zheng, W.; Xia, X.; et al. 2022. GLM-130B: An open bilingual pre-trained model. arXiv preprint
arXiv:2210.02414.
Cone: Cone embeddings for multi-hop reasoning over knowledge graphs
- Z Zhang
- J Wang
- J Chen
- S Ji
- F Wu
Zhang, Z.; Wang, J.; Chen, J.; Ji, S.; and Wu, F. 2021. Cone:
Cone embeddings for multi-hop reasoning over knowledge
graphs. In Advances in Neural Information Processing Systems.
Can chatgpt understand too?
- Q Zhong
- L Ding
- J Liu
- B Du
- D Tao
Zhong, Q.; Ding, L.; Liu, J.; Du, B.; and Tao, D. 2023b. Can
chatgpt understand too? a comparative study on chatgpt and
fine-tuned bert. arXiv preprint arXiv:2302.10198.