Generative Interpretability via Scalable Neuro-Symbolic Models

• URL: http://arxiv.org/abs/2609.13529v1
• Date: Fri, 11 Sep 2026 20:54:08 GMT
• Title: Generative Interpretability via Scalable Neuro-Symbolic Models
• Abstract summary: We argue for a shift toward generative interpretability.<n>We show the merits of generative interpretability as comparison to other interpretability research paradigms.
• Score: 2.1550607598300617
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As the use of Large Language Models moves from chatbots into agentic systems, where outputs become actions with irreversible consequences on reality, the existing paradigm on AI Interpretability research, post-hoc interpretability, is structurally inadequate for safe and trustworthy model deployment: it explains behavior after the fact but cannot audit or intervene in an inference computation before it commits to an output. We therefore argue for a shift toward \emph{generative interpretability}, an architectural property under which a model's inference pass natively exposes semantically meaningful checkpoints that are human-understandable and amenable to causal intervention. We show the merits of generative interpretability as comparison to other interpretability research paradigms, and propose Neuro-Symbolic Models as a concrete instantiation.

Related papers

• The Invisible Editorial Layer: Formalizing Undisclosed Inference-Time Steering, Probability Placement, and the Attribution Problem in Deployed Language Models [0.0]
  Evaluations of generative language models frequently interpret observable behavioral traits, such as political stance, brand inclination, and normative framing, as manifestations of model weights, post-training alignment, or prompting.<n>We examine inference-time framing bias: systematic steering of generated text toward institutional, ideological, or commercial frames without requiring changes to the underlying model parameters.<n>We argue that governance of generative systems must increasingly distinguish between auditing a model and auditing the deployed system that ultimately speaks.
  arXiv  Detail & Related papers  (2026-08-25T15:05:19Z)
• PACE: A Neuro-Symbolic Framework for Plausible and Actionable Counterfactual Explanations [0.0]
  PACE is a modular neuro-symbolic framework for generating feasibility-aware counterfactual explanations.<n>By explicitly modeling feasible interventions, the framework produces explanations consistent with domain knowledge.<n>Results highlight the trade-off between counterfactual validity and plausibility.
  arXiv  Detail & Related papers  (2026-07-01T16:55:06Z)
• Taming the Centaur(s) with LAPITHS: a framework for a theoretically grounded interpretation of AI performances [0.0]
  We introduce a framework called LAPITHS (Language model Analysis through Paradigm grounded Interpretations of Theses about Human likenesS)<n>We use it to show that several major claims advanced by models such as CENTAUR, proposed as an artificial Unified Model of Cognition, are not theoretically or empirically justified.
  arXiv  Detail & Related papers  (2026-04-30T14:29:50Z)
• Emergent Structured Representations Support Flexible In-Context Inference in Large Language Models [77.98801218316505]
  Large language models (LLMs) exhibit emergent behaviors suggestive of human-like reasoning.<n>We investigate the internal processing of LLMs during in-context concept inference.
  arXiv  Detail & Related papers  (2026-02-08T03:14:39Z)
• Internal Causal Mechanisms Robustly Predict Language Model Out-of-Distribution Behaviors [61.92704516732144]
  We show that the most robust features for correctness prediction are those that play a distinctive causal role in the model's behavior.<n>We propose two methods that leverage causal mechanisms to predict the correctness of model outputs.
  arXiv  Detail & Related papers  (2025-05-17T00:31:39Z)
• Neural Interpretable Reasoning [12.106771300842945]
  We formalize a novel modeling framework for achieving interpretability in deep learning.<n>We show that this complexity can be mitigated by treating interpretability as a Markovian property.<n>We propose a new modeling paradigm -- neural generation and interpretable execution.
  arXiv  Detail & Related papers  (2025-02-17T10:33:24Z)
• Causality can systematically address the monsters under the bench(marks) [64.36592889550431]
  Benchmarks are plagued by various biases, artifacts, or leakage.<n>Models may behave unreliably due to poorly explored failure modes.<n> causality offers an ideal framework to systematically address these challenges.
  arXiv  Detail & Related papers  (2025-02-07T17:01:37Z)
• Gumbel Counterfactual Generation From Language Models [64.55296662926919]
  We show that counterfactual reasoning is conceptually distinct from interventions.<n>We propose a framework for generating true string counterfactuals.<n>We show that the approach produces meaningful counterfactuals while at the same time showing that commonly used intervention techniques have considerable undesired side effects.
  arXiv  Detail & Related papers  (2024-11-11T17:57:30Z)
• Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness [68.69369585600698]
  Deep learning models often suffer from a lack of interpretability due to polysemanticity. Recent advances in monosemanticity, where neurons correspond to consistent and distinct semantics, have significantly improved interpretability. We show that monosemantic features not only enhance interpretability but also bring concrete gains in model performance.
  arXiv  Detail & Related papers  (2024-10-27T18:03:20Z)
• Meaning Representations from Trajectories in Autoregressive Models [106.63181745054571]
  We propose to extract meaning representations from autoregressive language models by considering the distribution of all possible trajectories extending an input text. This strategy is prompt-free, does not require fine-tuning, and is applicable to any pre-trained autoregressive model. We empirically show that the representations obtained from large models align well with human annotations, outperform other zero-shot and prompt-free methods on semantic similarity tasks, and can be used to solve more complex entailment and containment tasks that standard embeddings cannot handle.
  arXiv  Detail & Related papers  (2023-10-23T04:35:58Z)
• Logical Satisfiability of Counterfactuals for Faithful Explanations in NLI [60.142926537264714]
  We introduce the methodology of Faithfulness-through-Counterfactuals. It generates a counterfactual hypothesis based on the logical predicates expressed in the explanation. It then evaluates if the model's prediction on the counterfactual is consistent with that expressed logic.
  arXiv  Detail & Related papers  (2022-05-25T03:40:59Z)
• Explainability in Process Outcome Prediction: Guidelines to Obtain Interpretable and Faithful Models [77.34726150561087]
  We define explainability through the interpretability of the explanations and the faithfulness of the explainability model in the field of process outcome prediction. This paper contributes a set of guidelines named X-MOP which allows selecting the appropriate model based on the event log specifications.
  arXiv  Detail & Related papers  (2022-03-30T05:59:50Z)
• A Meta-Bayesian Model of Intentional Visual Search [0.0]
  We propose a computational model of visual search that incorporates Bayesian interpretations of the neural mechanisms that underlie categorical perception and saccade planning. To enable meaningful comparisons between simulated and human behaviours, we employ a gaze-contingent paradigm that required participants to classify occluded MNIST digits through a window that followed their gaze. Our model is able to recapitulate human behavioural metrics such as classification accuracy while retaining a high degree of interpretability, which we demonstrate by recovering subject-specific parameters from observed human behaviour.
  arXiv  Detail & Related papers  (2020-06-05T16:10:35Z)

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.