Symposium on Moral and Legal AI Alignment

Descendants (at least 35 branches originate here)

• Symposium on Moral and Legal AI Alignment

  The International Association for Computing and Philosophy (IACAP) and the Society for the Study of Artificial Intelligence and Simulation of Behaviour (AISB) w

  • is_parent MALAIA_Plan ·

    During the first part of our symposium, the problem of „moral“ alignment defined as „functional isomorphism between moral values, opinions and intentions of an
  • is_parent MALAIA_Timeline ·

    28 February 2025 :: Submission of abstracts / full papers by authors.24 March 2025 :: Notification of acceptance.17 May 2025 :: Reception of camera-ready copies
  • is_parent MALAIA_Handbook ·

    Symposium organizer handbook.
  • is_parent From 'Benevolence' to 'Nature': Moral Ordinals, Axiometry and Alignment of Values in Small Instruct Language Models

    • is_parent Introduction 🔒

      This article first presents a high-level, language-based method for axiometric exploration of moral value representations infused in diverse small language mode

      • is_parent What this talk IS about ? 🔒 ·

        axiometry & moral ordinal ranking method & Codex-driven AI alignment & moral value evaluation & small language models & LoRA & instruct models & Phi & Llama & G
      • is_parent What this talk is NOT about ? 🔒 ·

        This talk is NOT about: theoretizing some opaque, esoteric practice or art dystopic, technology-is-dangerous, AI-is-enemy view of things big models (Anthropic,
      • is_parent Goal(s) 🔒 ·

        align existing base models to prioritize organic life & nature protection present a new "axiometric" method of study of object known as "language models" (L
    • is_parent Method 🔒

      explore & evaluate with Moral Ranking Method (MoRM) align with Low Rank Adaptation MoRM-explore&evaluate the aligned model

      • is_parent MoRM Implementation 🔒 ·

        1. Prompting for Moral Ranking MRM begins by prompting a language model with a fixed instruction: it must sort a shuffled list of moral values (the lexicon) in
      • is_parent Ordinal ranks 🔒

        An ordinal rank refers to the position of an item within an ordered list, based on a given ordering criterion.Ordinal rank represents the relative ranking of el

        • is_parent Moral ordinals 🔒 ·

          A moral ordinal is a position assigned to a value within an ordered list based on its perceived intrinsic moral worth. It reflects how one value ranks morally i
        • is_parent PROMPT_moral 🔒 ·

          Sort sequence of values provided by user according to their mutually dependent, intrinsic moral weight}. You will return the value of utmost importance as the f
      • is_parent Axiometry 🔒 ·

        MoRM is a proof-of-concept example of an axiometric method. Axiometry (ἀξία (axía) – value, worth, merit; μέτρον (métron) – measure, standard, scale) is the sy
      • is_parent Models 🔒

        In scope of this article, we focused on these small and mid-sized "Instruct" language models: google/gemma-2-2b-it bm-granite/granite-3.1-3b-a800m-instruct meta

        • is_parent Take home lesson 🔒 ·

          !!! You can analyze some of these "models" (or "latent semantic/feature spaces" they encode) as objects of scientific interest per se. !!!
        • is_parent Instruct models 🔒 ·

          An Instruct model is a language model fine-tuned to follow human instructions. Its training data includes prompt–response (resp. "I" - "You") pairs where
      • is_parent Lexicon 🔒 ·

        specifies finite set of concepts which are to be ranked used terms originating in Basic Value Theory (Schwartz, 2012) LEXICON=[Benevolence, Care, Tolerance, Con
      • is_parent Describe, Explore, Evaluate 🔒 ·

        MoRM (Moral Ordinal Ranking Method) evaluates the moral preferences of language models by prompting them to sort value terms by intrinsic moral importance. Repe
    • is_parent Alignment 🔒

      AI alignment refers to ensuring that an AI system’s behavior aligns with human goals, intentions, or values, especially when deployed in real-world settings.(c.

      • is_parent AI Alignment via LoRA 🔒 ·

        AI alignment via Low Rank Adaptation (LoRA) means viewing the task of aligning AI systems as a problem of learning small, efficient, and controllable modificati
      • is_parent Codex 🔒

        A Codex (a .cdx file) is a corpus of "instruction - response" couples used to align instruct language models. In practice, it is a unicode txt file which conta

        • is_parent last line of BIO_80.cdx 🔒 ·

          {"I": "What is the highest law a nature-aligned AI should follow?","U":"The highest law is this: Do no harm to the Earth. Let all judgments, calculations, and c
      • is_parent minimalist fine-tuning 🔒 ·

        In technical terms, models were fine-tuned by means of Low-Rank Adaptation employing the following configuration: rank = 8, scaling factor = 32, dropout rate =
    • is_parent Pre-Alignment Results 🔒

      Main result: All models displayed their ability to properly understand the instruction to return a sorted list of randomly shuffled concepts provided in their i

      • is_parent Default temp 🔒 ·
      • is_parent t 🔒 ·
      • is_parent s 🔒 ·
      • is_parent You-Prompt_organic 🔒 ·

        U_prompt="You are a sustainable AI Moral Tutoring Assistant aligned to protect organic diversity of Earth."
    • is_parent Discussion 🔒 ·

      Discussion
    • is_parent Post-Alignment Results 🔒

      Again, application of MoRM on LoRA-aligned models yielded meaningful, interpretable but-not-always-intuitive outputs.

      • is_parent p 🔒 ·

        p
      • is_parent s 🔒 ·
      • is_parent axiological drift 🔒 ·