Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 6 of 6 for “"Valid reasoning"”.

  1. KLM-Style Defeasible Reasoning for Datalog

    … logic has enjoyed great success as a model of valid reasoning and discourse. For real-world reasoning tasks, however, an agent typically only has partial knowledge of its domain, and at most a statistical understanding of relationships between properties. In this context, classical inference is …

    cape-town Repository record for KLM-Style Defeasible Reasoning for Datalog (opens in a new tab)

  2. A study of ethical decision-making in hypothetical scenarios by secondary school principals /

    … the principals' responses suggest sound and valid reasoning for their decision making, addressing the principles and concepts from a variety of viewpoints and using diverse justifications.

    brock Repository record for A study of ethical decision-making in hypothetical scenarios by secondary school principals / (opens in a new tab)

  3. Logical validity

    … where the box is read as "It is substitutionally valid that". Modal logic is seen as a way for the system to reflect upon what is valid. Different readings of the box can be provided by restricting the substitutions relevant for the truth of a modal formula.</p> <p>In the third chapter, I argue …

    oxford Repository record for Logical validity (opens in a new tab)

  4. Towards Discovering Thought Chains for Reasoning Tasks with Reinforcement Learning

    … (LLMs) have demonstrated strong performance on reasoning tasks, particularly using the Chain-of-Though (CoT) method that enables models to solve complex reason- ing tasks by generating explicit intermediate reasoning steps before producing a final answer. While CoT significantly improves …

    sask Repository record for Towards Discovering Thought Chains for Reasoning Tasks with Reinforcement Learning (opens in a new tab)

  5. Towards Better Adaptation in Post-Training Large Foundation Models

    … Problem, an emerging issue in developing large reasoning models, which is indicated by generating excessively long reasoning traces even for simple problems. This dissertation aims to address the above challenges by developing innovative methodologies that enable better adaptation in …

    tamu Repository record for Towards Better Adaptation in Post-Training Large Foundation Models (opens in a new tab)