Robust Knowledge Extraction from Large Language Models using Social Choice Theory

• URL: http://arxiv.org/abs/2312.14877v2
• Date: Thu, 8 Feb 2024 17:29:54 GMT
• Title: Robust Knowledge Extraction from Large Language Models using Social Choice Theory
• Authors: Nico Potyka, Yuqicheng Zhu, Yunjie He, Evgeny Kharlamov, Steffen Staab
• Abstract summary: Large-language models (LLMs) can support a wide range of applications like conversational agents, creative writing or general query answering. They are ill-suited for query answering in high-stake domains like medicine because they are typically not robust. We propose using ranking queries repeatedly and to aggregate the queries using methods from social choice theory.
• Score: 18.634845632109496
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Large-language models (LLMs) can support a wide range of applications like conversational agents, creative writing or general query answering. However, they are ill-suited for query answering in high-stake domains like medicine because they are typically not robust - even the same query can result in different answers when prompted multiple times. In order to improve the robustness of LLM queries, we propose using ranking queries repeatedly and to aggregate the queries using methods from social choice theory. We study ranking queries in diagnostic settings like medical and fault diagnosis and discuss how the Partial Borda Choice function from the literature can be applied to merge multiple query results. We discuss some additional interesting properties in our setting and evaluate the robustness of our approach empirically.

Related papers

• Aligning Query Representation with Rewritten Query and Relevance Judgments in Conversational Search [32.35446999027349]
  We leverage both rewritten queries and relevance judgments in the conversational search data to train a better query representation model. The proposed model -- Query Representation Alignment Conversational Retriever, QRACDR, is tested on eight datasets.
  arXiv  Detail & Related papers  (2024-07-29T17:14:36Z)
• Optimization of Retrieval-Augmented Generation Context with Outlier Detection [0.0]
  We focus on methods to reduce the size and improve the quality of the prompt context required for question-answering systems. Our goal is to select the most semantically relevant documents, treating the discarded ones as outliers. It was found that the greatest improvements were achieved with increasing complexity of the questions and answers.
  arXiv  Detail & Related papers  (2024-07-01T15:53:29Z)
• UQE: A Query Engine for Unstructured Databases [71.49289088592842]
  We investigate the potential of Large Language Models to enable unstructured data analytics. We propose a new Universal Query Engine (UQE) that directly interrogates and draws insights from unstructured data collections.
  arXiv  Detail & Related papers  (2024-06-23T06:58:55Z)
• Database-Augmented Query Representation for Information Retrieval [59.57065228857247]
  We present a novel retrieval framework called Database-Augmented Query representation (DAQu) DAQu augments the original query with various (query-related) metadata across multiple tables. We validate DAQu in diverse retrieval scenarios that can incorporate metadata from the relational database.
  arXiv  Detail & Related papers  (2024-06-23T05:02:21Z)
• Generating Multi-Aspect Queries for Conversational Search [6.974395116689502]
  We show that the same retrieval model would perform better with more than one rewritten query by 85% in terms of nDCG@3. We propose a multi-aspect query generation and retrieval framework, called MQ4CS.
  arXiv  Detail & Related papers  (2024-03-28T10:40:22Z)
• Selecting Query-bag as Pseudo Relevance Feedback for Information-seeking Conversations [76.70349332096693]
  Information-seeking dialogue systems are widely used in e-commerce systems. We propose a Query-bag based Pseudo Relevance Feedback framework (QB-PRF) It constructs a query-bag with related queries to serve as pseudo signals to guide information-seeking conversations.
  arXiv  Detail & Related papers  (2024-03-22T08:10:32Z)
• Getting MoRE out of Mixture of Language Model Reasoning Experts [71.61176122960464]
  We propose a Mixture-of-Reasoning-Experts (MoRE) framework that ensembles diverse specialized language models. We specialize the backbone language model with prompts optimized for different reasoning categories, including factual, multihop, mathematical, and commonsense reasoning. Our human study confirms that presenting expert predictions and the answer selection process helps annotators more accurately calibrate when to trust the system's output.
  arXiv  Detail & Related papers  (2023-05-24T02:00:51Z)
• Query2Particles: Knowledge Graph Reasoning with Particle Embeddings [49.64006979045662]
  We propose a query embedding method to answer complex logical queries on knowledge graphs with missing edges. The answer entities are selected according to the similarities between the entity embeddings and the query embedding. A complex KG query answering method, Q2P, is proposed to retrieve diverse answers from different areas over the embedding space.
  arXiv  Detail & Related papers  (2022-04-27T11:16:08Z)
• Query Embedding on Hyper-relational Knowledge Graphs [0.4779196219827507]
  Multi-hop logical reasoning is an established problem in the field of representation learning on knowledge graphs. We extend the multi-hop reasoning problem to hyper-relational KGs allowing to tackle this new type of complex queries.
  arXiv  Detail & Related papers  (2021-06-15T14:08:50Z)
• Answering Counting Queries over DL-Lite Ontologies [0.0]
  We introduce a general form of counting query, relate it to previous proposals, and study the complexity of answering such queries. We consider some practically relevant restrictions, for which we establish improved complexity bounds.
  arXiv  Detail & Related papers  (2020-09-02T11:10:21Z)
• Query Focused Multi-Document Summarization with Distant Supervision [88.39032981994535]
  Existing work relies heavily on retrieval-style methods for estimating the relevance between queries and text segments. We propose a coarse-to-fine modeling framework which introduces separate modules for estimating whether segments are relevant to the query. We demonstrate that our framework outperforms strong comparison systems on standard QFS benchmarks.
  arXiv  Detail & Related papers  (2020-04-06T22:35:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.