Building Trustworthy AI by Addressing its 16+2 Desiderata with Goal-Directed Commonsense Reasoning

• URL: http://arxiv.org/abs/2506.12667v1
• Date: Sun, 15 Jun 2025 00:09:12 GMT
• Title: Building Trustworthy AI by Addressing its 16+2 Desiderata with Goal-Directed Commonsense Reasoning
• Abstract summary: Sub-symbolic machine learning algorithms simulate reasoning but hallucinate.<n>Rule-based reasoners are able to provide the chain of reasoning steps but are complex and use a large number of reasoners.<n>We propose s(CASP), a goal-directed constraint-based answer set programming reasoner.
• Score: 1.1584245758108584
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Current advances in AI and its applicability have highlighted the need to ensure its trustworthiness for legal, ethical, and even commercial reasons. Sub-symbolic machine learning algorithms, such as the LLMs, simulate reasoning but hallucinate and their decisions cannot be explained or audited (crucial aspects for trustworthiness). On the other hand, rule-based reasoners, such as Cyc, are able to provide the chain of reasoning steps but are complex and use a large number of reasoners. We propose a middle ground using s(CASP), a goal-directed constraint-based answer set programming reasoner that employs a small number of mechanisms to emulate reliable and explainable human-style commonsense reasoning. In this paper, we explain how s(CASP) supports the 16 desiderata for trustworthy AI introduced by Doug Lenat and Gary Marcus (2023), and two additional ones: inconsistency detection and the assumption of alternative worlds. To illustrate the feasibility and synergies of s(CASP), we present a range of diverse applications, including a conversational chatbot and a virtually embodied reasoner.

Related papers

• Provably Secure Agent Guardrail [89.79561918065122]
  Existing defense architectures rely on empirical semantic guardrails and probabilistic large model adjudicators.<n>This paper proposes a new security paradigm for agents based on the fundamental limitations of logical reasoning.
  arXiv  Detail & Related papers  (2026-05-28T02:12:41Z)
• Trustworthy AI Suffers from Invariance Conflicts and Causality is The Solution [80.98492754957466]
  Core trustworthy AI objectives, such as fairness, robustness, privacy, and explainability, are hard to achieve simultaneously.<n>This paper argues that causality is necessary to understand and balance trade-offs in performance and multiple objectives of trustworthy AI.
  arXiv  Detail & Related papers  (2026-05-04T14:26:28Z)
• Position: agentic AI orchestration should be Bayes-consistent [92.04373485710285]
  This paper argues that coherent decision-making requires Bayesian principles at the orchestration level of the agentic system.<n>It provides examples and design patterns to illustrate how beliefs and utility-aware policies can improve agentic AI orchestration.
  arXiv  Detail & Related papers  (2026-05-01T15:43:43Z)
• Argumentative Human-AI Decision-Making: Toward AI Agents That Reason With Us, Not For Us [25.806044355311553]
  We argue that the convergence of these fields will lay the foundation for a new paradigm: Argumentative Human-AI Decision-Making.<n>We analyze how the synergy of argumentation framework mining, argumentation framework synthesis, and argumentative reasoning enables agents that do not just justify decisions, but engage in dialectical processes where decisions are contestable and revisable.
  arXiv  Detail & Related papers  (2026-03-16T21:51:36Z)
• Why Avoid Generative Legal AI Systems? Hallucination, Overreliance, and their Impact on Explainability [0.0]
  This article argues that the deployment of generative AI systems in legal profession requires strong restraint due to the critical risks of hallucination and overreliance.<n>Central to this analysis is the definition of Generative Legal AI (GLAI), an umbrella term for systems specifically adapted for the legal domain.
  arXiv  Detail & Related papers  (2026-03-16T21:40:43Z)
• A Survey of Reasoning in Autonomous Driving Systems: Open Challenges and Emerging Paradigms [49.66022971508878]
  We argue that reasoning should be elevated from a modular component to the system's cognitive core.<n>We derive and systematize seven core reasoning challenges, such as the responsiveness-reasoning trade-off and social-game reasoning.<n>We identify a fundamental and unresolved tension between the high-latency, deliberative nature of LLM-based reasoning and the millisecond-scale, safety-critical demands of vehicle control.
  arXiv  Detail & Related papers  (2026-03-11T07:40:53Z)
• Defining Explainable AI for Requirements Analysis [0.0]
  Explainable Artificial Intelligence (XAI) has become popular in the last few years.<n>For AI to be trusted, it must demonstrate good performance in its decisionmaking.<n>Different applications have different requirements on the information required of the underlying AI system.
  arXiv  Detail & Related papers  (2026-02-22T07:05:49Z)
• Towards Generalizable Reasoning: Group Causal Counterfactual Policy Optimization for LLM Reasoning [50.352417879912515]
  Large language models (LLMs) excel at complex tasks with advances in reasoning capabilities.<n>We propose Group Causal Counterfactual Policy Optimization to explicitly train LLMs to learn generalizable reasoning patterns.<n>We then construct token-level advantages from this reward and optimize the policy, encouraging LLMs to favor reasoning patterns that are process-valid and counterfactually robust.
  arXiv  Detail & Related papers  (2026-02-06T08:03:11Z)
• Thinking Longer, Not Always Smarter: Evaluating LLM Capabilities in Hierarchical Legal Reasoning [11.255428720705204]
  We propose a framework that decomposes the process of identifying significant distinctions between cases into three-stage reasoning tasks.<n>Our framework models cases using factual predicates called factors, organizes them into a legal knowledge hierarchy, and defines verifiable rules for identifying distinctions.<n>We find that models consistently expend more computational resources on incorrect responses than correct ones, suggesting that "thinking longer" does not always mean "thinking smarter"
  arXiv  Detail & Related papers  (2025-10-09T18:15:28Z)
• Judicial Requirements for Generative AI in Legal Reasoning [0.0]
  Large Language Models (LLMs) are being integrated into professional domains, yet their limitations in high-stakes fields like law remain poorly understood.<n>This paper defines the core capabilities that an AI system must possess to function as a reliable reasoning tool in judicial decision-making.
  arXiv  Detail & Related papers  (2025-08-26T09:56:26Z)
• Rigor in AI: Doing Rigorous AI Work Requires a Broader, Responsible AI-Informed Conception of Rigor [83.99510317617694]
  We argue that a broader conception of what rigorous AI research and practice should entail is needed.<n>We aim to provide useful language and a framework for much-needed dialogue about the AI community's work.
  arXiv  Detail & Related papers  (2025-06-17T15:44:41Z)
• Towards A Litmus Test for Common Sense [5.280511830552275]
  This paper is the second in a planned series aimed at envisioning a path to safe and beneficial artificial intelligence.<n>We propose a more formal litmus test for common sense, adopting an axiomatic approach that combines minimal prior knowledge constraints with diagonal or Godel-style arguments.
  arXiv  Detail & Related papers  (2025-01-17T02:02:12Z)
• Artificial Expert Intelligence through PAC-reasoning [21.91294369791479]
  Artificial Expert Intelligence (AEI) seeks to transcend the limitations of both Artificial General Intelligence (AGI) and narrow AI.<n>AEI seeks to integrate domain-specific expertise with critical, precise reasoning capabilities akin to those of top human experts.
  arXiv  Detail & Related papers  (2024-12-03T13:25:18Z)
• Distilling Reasoning Ability from Large Language Models with Adaptive Thinking [54.047761094420174]
  Chain of thought finetuning (cot-finetuning) aims to endow small language models (SLM) with reasoning ability to improve their performance towards specific tasks. Most existing cot-finetuning methods adopt a pre-thinking mechanism, allowing the SLM to generate a rationale before providing an answer. This mechanism enables SLM to analyze and think about complex questions, but it also makes answer correctness highly sensitive to minor errors in rationale. We propose a robust post-thinking mechanism to generate answers before rationale.
  arXiv  Detail & Related papers  (2024-04-14T07:19:27Z)
• A Closer Look at the Self-Verification Abilities of Large Language Models in Logical Reasoning [73.77088902676306]
  We take a closer look at the self-verification abilities of large language models (LLMs) in the context of logical reasoning. Our main findings suggest that existing LLMs could struggle to identify fallacious reasoning steps accurately and may fall short of guaranteeing the validity of self-verification methods.
  arXiv  Detail & Related papers  (2023-11-14T07:13:10Z)
• Towards CausalGPT: A Multi-Agent Approach for Faithful Knowledge Reasoning via Promoting Causal Consistency in LLMs [55.66353783572259]
  Causal-Consistency Chain-of-Thought harnesses multi-agent collaboration to bolster the faithfulness and causality of foundation models.<n>Our framework demonstrates significant superiority over state-of-the-art methods through extensive and comprehensive evaluations.
  arXiv  Detail & Related papers  (2023-08-23T04:59:21Z)
• The Case Against Explainability [8.991619150027264]
  We show end-user Explainability's inadequacy to fulfil reason-giving's role in law. We find that end-user Explainability excels in the fourth function, a quality which raises serious risks. This study calls upon regulators and Machine Learning practitioners to reconsider the widespread pursuit of end-user Explainability.
  arXiv  Detail & Related papers  (2023-05-20T10:56:19Z)
• Cybertrust: From Explainable to Actionable and Interpretable AI (AI2) [58.981120701284816]
  Actionable and Interpretable AI (AI2) will incorporate explicit quantifications and visualizations of user confidence in AI recommendations. It will allow examining and testing of AI system predictions to establish a basis for trust in the systems' decision making.
  arXiv  Detail & Related papers  (2022-01-26T18:53:09Z)
• CausalCity: Complex Simulations with Agency for Causal Discovery and Reasoning [68.74447489372037]
  We present a high-fidelity simulation environment that is designed for developing algorithms for causal discovery and counterfactual reasoning. A core component of our work is to introduce textitagency, such that it is simple to define and create complex scenarios. We perform experiments with three state-of-the-art methods to create baselines and highlight the affordances of this environment.
  arXiv  Detail & Related papers  (2021-06-25T00:21:41Z)
• Argumentation-based Agents that Explain their Decisions [0.0]
  We focus on how an extended model of BDI (Beliefs-Desires-Intentions) agents can be able to generate explanations about their reasoning. Our proposal is based on argumentation theory, we use arguments to represent the reasons that lead an agent to make a decision. We propose two types of explanations: the partial one and the complete one.
  arXiv  Detail & Related papers  (2020-09-13T02:08:10Z)
• Reasonable Machines: A Research Manifesto [0.0]
  A sound ecosystem of trust requires ways for autonomously justify their actions. Building on social reasoning models such as moral and legal philosophy. Enabling normative communication creates trust and opens new dimensions of AI application.
  arXiv  Detail & Related papers  (2020-08-14T08:51:33Z)

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.