KI-Startseite

Weitere Themen
KI-Interessierte auf DIN.ONE

You are viewing an old version of this page. View the current version.

Compare with Current View Page History

« Previous Version 38 Next »

First draft to be created until 11 October 2024.

ADD NEW TOP LEVEL SECTION: LLM TRAINING

How do I enhance/augment/extend LLM training through KGs? (LLM TRAINING) – length: up to one page

Lead: Daniel Baldassare

Contributors:

  • Diego Collarana (FIT)
  • Daniel Baldassare (doctima) – Lead
  • Michael Wetzel (Coreon)
  • Rene Pietzsch (ECC)


Problem statement

The training of large language models typically employs unsupervised methods on extensive datasets. Despite their impressive performance on a range of tasks, these models often lack the practical, real-world knowledge required for certain applications. Furthermore, since domain-specific data is not included in the public domain datasets used for pre-training or fine-tuning large language models (LLMs), the integration of knowledge graphs (KGs) becomes fundamental for the injection of proprietary knowledge into LLMs, especially for enterprise solutions. In order to infuse this knowledge into LLMs during training, many techniques have been researched in recent years, resulting in three main state-of-the-art methods (Pan et al, 2024): 

  1. Integration of KGs into training objectives (See answer 1)
  2. Verbalization of KGs into LLM inputs (See answer 2)
  3.  Integrate KGs by Fusion Modules: Joint training of graph and language models (See answer 3)

Explanation of concepts

The first method focuses on extending the pre-training procedure. The term pretraining objectives is used to describe the techniques that guide the learning process of a model from its training data. In the context of pre-training large language models, a variety of methods have been employed based on the architecture of the model itself. Decoder-only models such as GPT-4 usually use Casual Language Modelling (CLM), where the model is presented with a sequence of tokens and learns to predict the next token in the sequence based solely on the preceding tokens (Wang et al., 2022). Integrating KGs into training objectives consists in extending the standard llm's pre-training objective of generating coherent and contextually relevant text by designing a knowledge aware pre-training.

The second method involves integrating KGs directly into the LLM's input by verbalising the knowledge graph into the prompt, thereby transforming structured data into text format that the LLM can process and learn from. Data from the knowledge is either prepended or postpended to the user's question as contextual information in the prompt. Within this approach the standard llm pre-training objective of generating coherent and contextually relevant text remains untouched and the knowledge augmentation task is modeled as a linguistic task.


Brief description of the state of the art

First draft to be created until 11 October 2024


Proposed solutions:

Answer 1: integrate KGs into the LLM Training Objective

Contributors:

  • Diego Collarana (FIT)

Short definition/description of this topic: please fill in ...

  • Content ...
  • Content ...
  • Content ... 

Answer 2: integrate KGs into LLM Inputs (verbalize KG for LLM training)

Contributors:

  • Diego Collarana (FIT)
  • Daniel Baldassare (doctima) – Lead
  • Michael Wetzel (Coreon)
  • Rene Pietzsch (ECC)
  • ... 

Draft from Daniel Baldassare :

Short definition/description of this topic: Verbalizing knowledge graphs for LLM is the task of representing knowledge graphs as text so that they can be written directly in the prompt, the main input source of LLM. Verbalization consists of finding textual representations for nodes, relationships between nodes, and their metadata. Verbalization can take place at different stages of the LLM lifecycle, during training (pre-training, instruction fine-tuning) or during inference (in-context learning), and consists in:

Answer 3: Integrate KGs by Fusion Modules

Contributors:

  • Diego Collarana (FIT)

Short definition/description of this topic: please fill in ...

  • Content ...
  • Content ...
  • Content ... 


References:

  • S. Pan, L. Luo, Y. Wang, C. Chen, J. Wang, und X. Wu, „Unifying Large Language Models and Knowledge Graphs: A Roadmap“, IEEE Trans. Knowl. Data Eng., Bd. 36, Nr. 7, S. 3580–3599, Juli 2024, doi: 10.1109/TKDE.2024.3352100.
  • T. Wang u. a., „What Language Model Architecture and Pretraining Objective Works Best for Zero-Shot Generalization?“, in Proceedings of the 39th International Conference on Machine Learning, PMLR, Juni 2022, S. 22964–22984. Zugegriffen: 3. Oktober 2024. [Online]. Verfügbar unter: https://proceedings.mlr.press/v162/wang22u.html



ADD NEW TOP LEVEL SECTION: ENHANCING LLMs AT INFERENCE TIME

How do I use KGs for Retrieval-Augmented Generation (RAG)? (2.1 – Prompt Enhancement) – length: up to one page

Lead: Diego Collarana 

Contributors:

  • Daniel Burkhardt (FSTI)
  • Robert David (SWC)
  • Diego Collarana (FIT)
  • Daniel Baldassare (doctima)
  • Michael Wetzel (Coreon)

Problem statement

RAG methods aim to enhance the capabilities of LLMs by providing real-time information and domain-specific knowledge that may not be present in their training data. Despite its advantages over standalone LLMs, Conventional RAG has the following limitations:

  1. Struggles to answer queries that require the intricate interconnectedness of information and global context crucial for generating comprehensive summaries.
  2. It cannot integrate structure and unstructured data, a use case typically required in industrial applications.
  3. Limited accuracy due to context loss during text chunking and its reliance on text similarity search.
  4. It has limited reasoning capabilities, especially with abstract questions that require reasoning, inference, or the synthesis of new information not explicitly stated in the source material.
  5. The answers cannot be backtracked to the information sources (factual grounding).
  6. The external knowledge, while consistent, can still lead to inconsistencies in the generated answer.

Explanation of concepts

  • Retrieval-augmented generation (RAG) methods combine retrieval mechanisms with generative models to enhance the output of LLMs by incorporating external knowledge. By grounding the generated output in specific and relevant information, RAG methods improve the quality and accuracy of the generated output.

  • Types of RAG:

    • Conventional RAG has three components: 1) Knowledge Base, typically created by chunking text documents, transforming them into embeddings, and storing them in a vector store. 2) Retriever searches the vector database for chunks that exhibit high similarity to the query. 3) Generator feeds the retrieved chunks, alongside the original query, to an LLM to generate the final response.
    • Graph RAG integrates knowledge graphs into the RAG framework, allowing for the retrieval of structured data that can provide additional context and factual accuracy to the generative model. 
      The retrieval can be done on any source with a semantic representation, e.g., documents with semantic annotations or relational data via OBDA or R2RML, thereby ingesting structured and unstructured source information into the Graph RAG.
  • RAG is used in various natural language processing tasks, including question-answering, information extraction, sentiment analysis, and summarization. It is particularly beneficial in scenarios requiring domain-specific knowledge.

Brief description of the state-of-the-art

The emerging field of Graph RAG develops methods to exploit the rich, structured relationships between entities within a KG to retrieve more precise, factually relevant context for LLMs [9]. Graph RAG methods encompass graph construction, knowledge retrieval, and answer-generation techniques [1,2,5]. We find methods that leverage existing open-source KGs [3] to methods for automatically building domain-specific KGs from raw textual data using LLMs [6]. The retrieval phase focuses on efficiently extracting pertinent subgraphs, paths, or nodes relevant to a user query with techniques like embedding similarity, pre-defined rules, or LLM-guided search. In the generation phase, retrieved graph information is transformed into LLM-compatible formats, such as graph languages, embeddings, or GNN encoding, to generate enriched and contextually grounded responses [4]. Recently, significant attention has been given to hybrid approaches combining conventional RAG and Graph RAG strengths [7,8]. HybridRAG integrates contextual information from traditional vector databases and knowledge graphs, resulting in a more balanced and effective system that surpasses individual RAG approaches in critical metrics like faithfulness, answer relevancy and context recall. 

We describe various solutions for integrating knowledge graphs into RAG systems to improve accuracy, reliability, and explainability. 

Answer 1: Knowledge Graph as a Database with Natural Language Queries (NLQ)

Description: This solution treats the knowledge graph as a structured database and leverages natural language queries (NLQ) to retrieve specific information. The implementation steps are as follows:

  • First, the user's question is processed to extract key entities and relationships using entity linking and relationship extraction techniques. (Natural Language Understanding)
  • Next, the natural language query is partially or fully mapped into a graph query language, e.g., Cypher or SPARQL. (Graph Query Construction)
  • Then, the constructed graph query is executed against the knowledge graph database, which retrieves precise and targeted information from the knowledge graph. (Knowledge Graph Execution)
  • Finally, the retrieved results are passed to the LLM for summarization or further processing to generate the final answer. (Response generation)

Considerations:

  • Accurate Query Mapping: Requires advanced NLP techniques to map natural language queries to graph queries accurately. Entity linking and relationship extraction must be precise to ensure correct query formulation.
  • Performance Efficiency: Executing complex graph queries may impact performance, especially with large-scale knowledge graphs. Optimization of graph databases and queries is necessary for real-time applications.
  • Scalability: The system should handle growing knowledge graphs without significant performance loss. Scalable graph database solutions are essential.
  • User Experience: The system must effectively interpret user intent from natural language inputs. Providing clear and concise answers enhances usability and trust.

Standards and Protocols:

  • Compliance with Data Standards: Ensure the knowledge graph adheres to relevant data modeling standards. Where applicable, utilize standardized vocabularies and ontologies.
  • Interoperability: Design the system for various graph databases and query languages. Support integration with external data sources and systems.

Answer 2: Knowledge Graph-Guided Retrieval Mechanisms

Description: KG-Guided Retrieval Mechanisms involve using, for example, knowledge graphs or vector databases to enhance the retrieval process in RAG systems. Knowledge graphs provide a structured representation of knowledge, enabling more precise and contextually aware information retrieval. This approach can directly query knowledge graphs or use them to augment queries to other data sources, improving the relevance and accuracy of the retrieved information.

  • First, the user's question is processed to extract key entities and relationships using entity linking and relationship extraction techniques as a (semantic) graph representation of the question. (Natural Language Understanding)
  • Next, the graph representation is executed against the knowledge graph database, which first retrieves information from the knowledge graph and then retrieves the associated mapped data source.
    Data sources can be of different kinds:
    • Knowledge graph data
    • Non-knowledge graph data with a graph representation:
      • Tabular and relational data, e.g., via OBDA or R2RML.
      • Semi-structured data, e.g., XML or DITA.
      • Unstructured natural language, e.g., via semantic annotations.
  • Then, the retrieved (different kinds of) results are consolidated (preprocessed) to be ingested into the LLM prompt. (Data consolidation)
  • Finally, the consolidated results are passed to the LLM for summarization or further processing to generate the final answer. (Response generation)

Considerations:

  • Limited input data: a short user's question poses a challenge to effectively create a graph representation sufficiently expressive for a high-quality retrieval of information.
  • Knowledge model: a high-quality graph representation of both the user question and the actual information in the database is very likely to need a knowledge model with sufficient expressivity in the background.
  • Graph representation: doing graph-based retrieval of (heterogeneous) data sources needs an established graph representation for each source.
  • Consolidation architecture: Setting up a system architecture for consolidated data sources needs different kinds of integration components.
  • Semantic gap: there is the risk of a gap of semantic information between the retrieved information and the LLM-generated answer, because any semantics contained in the knowledge graph and any knowledge model cannot be preserved during ingestion into the LLM generation.

Standards and Protocols:

  • Compliance with Data Standards: Ensure the knowledge graph adheres to relevant data modeling standards. Where applicable, utilize standardized vocabularies and ontologies.
  • Interoperability: Design the system for various graph databases and query languages. Support integration with external data sources and systems.

Answer 3: Hybrid RAG Combining KGs and Dense Vectors

Draft from Daniel Burkhardt: 

Description: Hybrid Retrieval combines the strengths of knowledge graphs and dense vector representations to improve information retrieval. This approach leverages the structured, relational data from knowledge graphs and the semantic similarity captured by dense vectors, resulting in enhanced retrieval capabilities. Hybrid retrieval systems can improve semantic understanding and contextual insights while addressing scalability and integration complexity challenges.

  • First, the user submits a query that is analyzed to select which retrieval approach (1.*) (Arbitrator or Classification)
  • The retrieval components are called either in parallel or sequentially (Hybrid Retrieval Process)
    • Vector Search: Retrieves data based on vector embeddings
    • Keyword Search: Retrieves data based on keyword matching
    • Graph Queries: Retrieves structured data from the knowledge graph
  • Then, we combine results from all retrieval methods. (Result Integration)
  • Response Generation: LLM generates and delivers the response.

Considerations:

  • Requires efficient result fusion techniques
  • Addresses diverse data types and sources
  • Increase in latency of response

REFERENCE TO BE REMOVED

Key Challenges

  • Knowledge Graph Construction and Maintenance: Creating and updating high-quality knowledge graphs for specific domains can be challenging and resource-intensive.
  • Scalability and Efficiency: Retrieving information from large and complex knowledge graphs while maintaining acceptable response times remains challenging.
  • Evaluation Standardization: The lack of widely accepted benchmarks and evaluation metrics hinders progress and comparability across Graph RAG approaches. The quality of KG is crucial.
  • Human Element, we need knowledge engineers and domain specialists. 

References

  • [1] Boci Peng, Yun Zhu, Yongchao Liu, Xiaohe Bo, Haizhou Shi, Chuntao Hong, Yan Zhang, Siliang Tang: Graph Retrieval-Augmented Generation: A Survey. CoRR abs/2408.08921 (2024)
  • [2] Diego Collarana, Moritz Busch, Christoph Lange: Knowledge Graph Treatments for Hallucinating Large Language Models. ERCIM News 2024(136) (2024)
  • [3] Junde Wu, Jiayuan Zhu, Yunli Qi: Medical Graph RAG: Towards Safe Medical Large Language Model via Graph Retrieval-Augmented Generation. CoRR abs/2408.04187 (2024)
  • [4] Sen, Priyanka, Sandeep Mavadia, and Amir Saffari. Knowledge graph-augmented language models for complex question answering. Proceedings of the 1st Workshop on Natural Language Reasoning and Structured Explanations - NLRSE (2023)
  • [5] Shirui Pan, Linhao Luo, Yufei Wang, Chen Chen, Jiapu Wang, Xindong Wu: Unifying Large Language Models and Knowledge Graphs: A Roadmap. IEEE Trans. Knowl. Data Eng. 36 (7) (2024)
  • [6] Darren Edge, Ha Trinh, Newman Cheng, Joshua Bradley, Alex Chao, Apurva Mody, Steven Truitt, Jonathan Larson: From Local to Global: A Graph RAG Approach to Query-Focused Summarization. CoRR abs/2404.16130 (2024)
  • [7] Bhaskarjit Sarmah, Benika Hall, Rohan Rao, Sunil Patel, Stefano Pasquali, Dhagash Mehta: HybridRAG: Integrating Knowledge Graphs and Vector Retrieval Augmented Generation for Efficient Information Extraction. CoRR abs/2408.04948 (2024)
  • [8] Jens Lehmann, Dhananjay Bhandiwad, Preetam Gattogi, Sahar Vahdati: Beyond Boundaries: A Human-like Approach for Question Answering over Structured and Unstructured Information Sources. Trans. Assoc. Comput. Linguistics (2024)
  • [9] Juan Sequeda, Dean Allemang, Bryon Jacob: A Benchmark to Understand the Role of Knowledge Graphs on Large Language Model's Accuracy for Question Answering on Enterprise SQL Databases. GRADES/NDA (2024)

How do I enhance LLM explainability by using KGs? (2.2 – Answer Verification) – length: up to one page

Lead: Daniel Burkhardt

Draft from Daniel Burkhardt

Problem Statement (one paragraph) 

KG-Enhanced LLM Interpretability refers to the use of knowledge graphs to improve the transparency and explainability of large LLMs. By integrating structured knowledge from KGs, LLMs can generate more interpretable outputs, providing justifications and factual accuracy checks for their responses. This integration helps in aligning LLM-generated knowledge with factual data, enhancing trust and reliability. 

Explanation of concepts 

Brief description of the state of the art (one paragraph) 


References

Answer 1: Measuring KG Alignment in LLM Representations

Draft from Daniel Burkhardt: 

Short definition/description of this topic: This involves evaluating how well the representations generated by LLMs align with the structured knowledge in KGs. This alignment is crucial for ensuring that LLMs can accurately incorporate and reflect the relationships and entities defined in KGs, thereby improving the factuality and coherence of their outputs.

literature: https://arxiv.org/abs/2311.06503 , https://arxiv.org/abs/2406.03746, https://arxiv.org/abs/2402.06764

Answer 2: KG-Guided Explanation Generation

Draft from Daniel Burkhardt: 

Short definition/description of this topic: KG-Guided Explanation Generation uses knowledge graphs to provide explanations for the outputs of LLMs. By leveraging the structured data and relationships within KGs, this approach can generate detailed and contextually relevant explanations, enhancing the interpretability and transparency of LLM outputs. 

literature: https://arxiv.org/abs/2312.00353, https://arxiv.org/abs/2403.03008

Contributors:

Answer 3: KG-Based Fact-Checking and Verification

Contributors:

  • Daniel Burkhardt (FSTI)
  • Robert David (SWC)

Draft from Daniel Burkhardt: 

literatur: https://arxiv.org/abs/2404.00942, https://aclanthology.org/2023.acl-long.895.pdf, https://arxiv.org/pdf/2406.01311 

Description: 

Short definition/description of this topic: This involves using knowledge graphs to verify the factual accuracy of information generated by LLMs. By cross-referencing LLM outputs with the structured data in KGs, this approach can identify and correct inaccuracies, ensuring that the generated information is reliable and trustworthy. 

  • First, the generated output is analysed regarding the knowledge graph and key entities and relationships are extracted to create a graph representation of the LLM answer.
  • Next, this graph representation is then analyzed regarding the knowledge graph used for retrieval and any knowledge models in the background are also included. The analysis retrieves a graph representation of an explanation or justification and is returned as a (sub)graph or graph traversal with any additional information added, like RDF* weights.
  • Finally, the explanation is then returned to the user in a human-readable way to be cross-checked with the LLM generated answer.

Considerations:

  • Limited input data: a short LLM generated answer poses a challenge to effectively backtrack sufficient information in the knowledge graph for a high-quality explanation.
  • Presentation: the explanation is graph-based data and difficult to explain or present to non-experts.

Standards and Protocols:

Query languages

Path retrieval

How do I enhance LLM reasoning through KGs? (2.3 – Answer Augmentation) – length: up to one page

Lead: Daniel Burkhardt

Draft from Daniel Burkhardt: 

Problem Statement (one paragraph) 

KG-Enhanced LLM Reasoning refers to the use of knowledge graphs to improve the reasoning capabilities of LLMs. By incorporating structured knowledge, LLMs can perform more complex reasoning tasks, such as multi-hop reasoning, where multiple pieces of information are connected to derive a conclusion.

Explanation of concepts 

Brief description of the state of the art (one paragraph) 


References


Answer 1: KG-Guided Multi-hop Reasoning

Contributors:

  • Daniel Burkhardt (FSTI)
  • Daniel Baldassare (doctima)

Short definition/description of this topic: This involves using knowledge graphs to facilitate multi-hop reasoning, where LLMs connect multiple entities and relationships to answer complex questions. This approach enhances the reasoning depth of LLMs by providing a structured path through interconnected data points in KGs.

literature: https://neo4j.com/developer-blog/knowledge-graphs-llms-multi-hop-question-answering/, https://link.springer.com/article/10.1007/s11280-021-00911-5

Answer 2: KG-Based Consistency Checking in LLM Outputs

Contributors:

  • Daniel Burkhardt (FSTI)
  • Daniel Baldassare (doctima)
  • Michael Wetzel (Coreon)


KG-Based Consistency Checking involves using knowledge graphs to ensure the consistency of LLM outputs. By comparing generated content with the structured data in KGs, this method can identify inconsistencies and improve the coherence of LLM-generated information.

literature:https://www.researchgate.net/publication/382363779_Knowledge-based_Consistency_Testing_of_Large_Language_Models

How do I evaluate LLMs through KGs? (3) – length: up to one page

First Version: Automatic evaluation of LLMs is usually done by cleverly comparing a desired result. The desired output can be evaluated using direct matching or similarity metrics (BLEU, N-gram, ROUGE, BERTScore). However, there are various reasons why KG can be used in the evaluation to support or enhance these evaluation techniques. 
Firstly, KG triplets can be extracted from the output of an LLM and then analyzed. The triplets can be compared with a KG to check factuality or knowledge coverage. Examples of this knowledge coverage would be political positions, cultural or sporting events, or current news information. Furthermore, the extracted KG triplets can be used to evaluate tasks/features where a similarity comparison of the LLM output is undesirable. This is the case for identifying and evaluating hallucinations of LLMs.
The second reason is to use KGs to enhance LLM inputs with relevant information. This method is beneficial, for example, if the goal is to use in-context learning to provide relevant information for a specific task to the LLM. In addition, planned adversarial attacks can be carried out on the LLM to uncover biases or weak points. 
Both variants are explained in more detail below as examples. 

Answer 1: Using KGs to Evaluate LLM Knowledge Coverage

Maybe add additional properties such as factuality, correctness, precision etc. or perhaps keep these that we have right now and call them "selected properties" ... 

Lead: Fabio

Contributors:

  • Daniel Burkhardt (FSTI)
  • Daniel Baldassare (doctima)
  • Fabio Barth (DFKI)
  • Max Ploner (HU)
  • ... 

Draft from Daniel Burkhardt: 

Short definition/description of this topic: This involves using knowledge graphs to analyze and evaluate various aspects of LLMs, such as knowledge coverage and biases. KGs provide a structured framework for assessing how well LLMs capture and represent knowledge across different domains. This involves assessing the extent to which LLMs cover the knowledge represented in KGs. By comparing LLM outputs with the structured data in KGs, this approach can identify gaps in knowledge and areas for improvement in LLM training and performance

First Version: The first evaluation process can be divided into two parts. Those can be executed through various techniques, which this section will not discuss. First, the LLM generates output sequences based on an evaluation set of input samples. Specific KG triplets are then identified and extracted from the generated output sequence. The variants for extraction and identification can be found in other subchapters of this DIN SPEC. The extracted KG triplets are usually domain or task-specific. These KG triplets are used to generate a KG. 
In the second step, the KG can now be analyzed. For instance, factuality can be checked by analyzing each KG triplet in the generated KG, given the context provided. Alternatively, the extracted KG triplets can be compared with an existing, more extensive KG to analyze the knowledge coverage of an LLM.


literature: https://www.amazon.science/publications/grapheval-a-knowledge-graph-based-llm-hallucination-evaluation-framework


Answer 2: Analyzing LLM Biases through KG Comparisons

Contributors:

  • Daniel Burkhardt (FSTI)
  • Daniel Baldassare (doctima)
  • Fabio Barth (DFKI)
  • ... 

Draft from Daniel Burkhardt: 

Short definition/description of this topic: This involves using knowledge graphs to identify and analyze biases in LLMs. By comparing LLM outputs with the neutral, structured data in KGs, this approach can highlight biases and suggest ways to mitigate them, leading to more fair and balanced AI systems.

First Version: In the second process, the inputs, i.e., the evaluation samples, are enhanced with information from a KG to provide helpful or misleading context. KG nodes must first be extracted from the samples using, for example, RAG. Then, based on the extracted KG nodes, the top k nodes can be determined from the KG using an arbitrarily efficient retrieval method. These nodes can then be used to enhance the input. For example, the nodes can be displayed as “superior knowledge” in the prompt in order to carry out adversarial attacks to obtain biased responses from open- and closed-source LLMs. Finally, the output of the model is analyzed. Again, different evaluation methods and metrics can be applied in the final step.

  • Content ...
  • Content ... 

literature: https://arxiv.org/abs/2405.04756

  • No labels