Forgetting That Sticks: Quantization-Permanent Unlearning via Circuit Attribution

Standard unlearning evaluations measure behavioral suppression in full precision, immediately after training, despite every deployed language model being quantized first. Recent work has shown that 4-bit post-training quantization can reverse machine unlearning; we show this is not a tuning artefact but a systematic dual failure: gradient-based methods that achieve meaningful forgetting lose it under compression, while methods that survive quantization barely change the model. Both failures trace to the same root cause: across all baselines, per-parameter updates lie 47-828x below the NF4 quantization bin width; updates diffused across billions of parameters cannot clear quantization bin boundaries, a consequence we formalize as a sparsity-permanence tradeoff. We present MANSU (Mechanistic-Aligned Null-Space Unlearning), which resolves both modes by combining causal circuit attribution to isolate the minimal forget-set subgraph, circuit-restricted null-space projection with a diagonal-Fisher retain bound, and a per-parameter magnitude floor guaranteeing quantization survival by construction. We additionally introduce Circuit Attribution Divergence (CAD), a mechanistic verification metric distinguishing structural erasure from behavioral suppression, a distinction existing metrics cannot make. Across multiple model families and hazard benchmarks, MANSU is the first method to jointly satisfy all four properties with margin on each (meaningful forgetting, retain preservation, non-positive PTQ gap, and structural erasure), while gradient-based baselines recover up to +0.05 accuracy under compression.

Position: Behavioural Assurance Cannot Verify the Safety Claims Governance Now Demands

This position paper argues that behavioural assurance, even when carefully designed, is being asked to carry safety claims it cannot verify. AI governance frameworks enacted between 2019 and early 2026 require reviewable evidence of properties such as the absence of hidden objectives, resistance to loss-of-control precursors, and bounded catastrophic capability; current assurance methodologies (primarily behavioural evaluations and red-teaming) are epistemically limited to observable model outputs and cannot verify the latent representations or long-horizon agentic behaviours these frameworks presume to regulate. We formalize this structural mismatch as the audit gap, the divergence between required and achievable verification access, and introduce the concept of fragile assurance to describe cases where the evidential structure does not support the asserted safety claim. Through an analysis of a 21-instrument inventory, we identify an incentive gradient where geopolitical and industrial pressures systematically reward surface-level behavioral proxies over deep structural verification. Finally, we propose a technical pivot: bounding the weight of behavioral evidence in legal text and extending voluntary pre-deployment access with mechanistic-evidence classes, specifically linear probes, activation patching, and before/after-training comparisons.

AlignTune: Modular Toolkit for Post-Training Alignment of Large Language Models

Post-training alignment is central to deploying large language models (LLMs), yet practical workflows remain split across backend-specific tools and ad-hoc glue code, making experiments hard to reproduce. We identify backend interference, reward fragmentation, and irreproducible pipelines as key obstacles in alignment research. We introduce AlignTune, a modular toolkit exposing a unified interface for supervised fine-tuning (SFT) and RLHF-style optimization with interchangeable TRL and Unsloth backends. AlignTune standardizes configuration, provides an extensible reward layer (rule-based and learned), and integrates evaluation over standard benchmarks and custom tasks. By isolating backend-specific logic behind a single factory boundary, AlignTune enables controlled comparisons and reproducible alignment experiments.

Beyond Uniform Credit: Causal Credit Assignment for Policy Optimization

Policy gradient methods for language model reasoning, such as GRPO and DAPO, assign uniform credit to all generated tokens - the filler phrase "Let me think" receives the same gradient update as the critical calculation "23 + 45 = 68." We propose counterfactual importance weighting: mask reasoning spans, measure the drop in answer probability, and upweight tokens accordingly during policy gradient updates. Our method requires no auxiliary models or external annotation, instead importance is estimated directly from the policy model's own probability shifts. Experiments on GSM8K across three models spanning the Qwen and Llama families demonstrate consistent improvements over uniform baselines and faster convergence to equivalent accuracy. Inverting the importance signal hurts performance, confirming we capture genuine causal structure rather than noise. Analysis shows the method correctly prioritizes calculation steps over scaffolding text. We view these findings as establishing counterfactual importance weighting as a foundation for further research rather than a complete solution.

$C$-$ΔΘ$: Circuit-Restricted Weight Arithmetic for Selective Refusal

Modern deployments require LLMs to enforce safety policies at scale, yet many controls rely on inference-time interventions that add recurring compute cost and serving complexity. Activation steering is widely used, but it requires runtime hooks and scales cost with the number of generations; conditional variants improve selectivity by gating when steering is applied but still retain an inference-time control path. We ask whether selective refusal can be moved entirely offline: can a mechanistic understanding of category-specific refusal be distilled into a circuit-restricted weight update that deploys as a standard checkpoint? We propose C-Δθ: Circuit Restricted Weight Arithmetic, which (i) localizes refusal-causal computation as a sparse circuit using EAP-IG and (ii) computes a constrained weight update ΔθC supported only on that circuit (typically <5% of parameters). Applying ΔθC yields a drop-in edited checkpoint with no inference-time hooks, shifting cost from per-request intervention to a one-time offline update. We evaluate category-targeted selectivity and capability retention on refusal and utility benchmarks.

Beyond KL Divergence: Policy Optimization with Flexible Bregman Divergences for LLM Reasoning

Policy optimization methods like Group Relative Policy Optimization (GRPO) and its variants have achieved strong results on mathematical reasoning and code generation tasks. Despite extensive exploration of reward processing strategies and training dynamics, all existing group-based methods exclusively use KL divergence for policy regularization, leaving the choice of divergence function unexplored. We introduce Group-Based Mirror Policy Optimization (GBMPO), a framework that extends group-based policy optimization to flexible Bregman divergences, including hand-designed alternatives (L2 in probability space) and learned neural mirror maps. On GSM8K mathematical reasoning, hand-designed ProbL2-GRPO achieves 86.7% accuracy, improving +5.5 points over the Dr. GRPO baseline. On MBPP code generation, neural mirror maps reach 60.1-60.8% pass@1, with random initialization already capturing most of the benefit. While evolutionary strategies meta-learning provides marginal accuracy improvements, its primary value lies in variance reduction ($\pm$0.2 versus $\pm$0.6) and efficiency gains (15% shorter responses on MBPP), suggesting that random initialization of neural mirror maps is sufficient for most practical applications. These results establish divergence choice as a critical, previously unexplored design dimension in group-based policy optimization for LLM reasoning.

Exploring Fine-Tuning for Tabular Foundation Models

Tabular Foundation Models (TFMs) have recently shown strong in-context learning capabilities on structured data, achieving zero-shot performance comparable to traditional machine learning methods. We find that zero-shot TFMs already achieve strong performance, while the benefits of fine-tuning are highly model and data-dependent. Meta-learning and PEFT provide moderate gains under specific conditions, whereas full supervised fine-tuning (SFT) often reduces accuracy or calibration quality. This work presents the first comprehensive study of fine-tuning in TFMs across benchmarks including TALENT, OpenML-CC18, and TabZilla. We compare Zero-Shot, Meta-Learning, Supervised (SFT), and parameter-efficient (PEFT) approaches, analyzing how dataset factors such as imbalance, size, and dimensionality affect outcomes. Our findings cover performance, calibration, and fairness, offering practical guidelines on when fine-tuning is most beneficial and its limitations.

Interpretability as Alignment: Making Internal Understanding a Design Principle

Large neural models are increasingly deployed in high-stakes settings, raising concerns about whether their behavior reliably aligns with human values. Interpretability provides a route to internal transparency by revealing the computations that drive outputs. We argue that interpretability especially mechanistic approaches should be treated as a design principle for alignment, not an auxiliary diagnostic tool. Post-hoc methods such as LIME or SHAP offer intuitive but correlational explanations, while mechanistic techniques like circuit tracing or activation patching yield causal insight into internal failures, including deceptive or misaligned reasoning that behavioral methods like RLHF, red teaming, or Constitutional AI may overlook. Despite these advantages, interpretability faces challenges of scalability, epistemic uncertainty, and mismatches between learned representations and human concepts. Our position is that progress on safe and trustworthy AI will depend on making interpretability a first-class objective of AI research and development, ensuring that systems are not only effective but also auditable, transparent, and aligned with human intent.

Bridging the Gap in XAI-Why Reliable Metrics Matter for Explainability and Compliance

This position paper emphasizes the critical gap in the evaluation of Explainable AI (XAI) due to the lack of standardized and reliable metrics, which diminishes its practical value, trustworthiness, and ability to meet regulatory requirements. Current evaluation methods are often fragmented, subjective, and biased, making them prone to manipulation and complicating the assessment of complex models. A central issue is the absence of a ground truth for explanations, complicating comparisons across various XAI approaches. To address these challenges, we advocate for widespread research into developing robust, context-sensitive evaluation metrics. These metrics should be resistant to manipulation, relevant to each use case, and based on human judgment and real-world applicability. We also recommend creating domain-specific evaluation benchmarks that align with the user and regulatory needs of sectors such as healthcare and finance. By encouraging collaboration among academia, industry, and regulators, we can create standards that balance flexibility and consistency, ensuring XAI explanations are meaningful, trustworthy, and compliant with evolving regulations.

xai_evals : A Framework for Evaluating Post-Hoc Local Explanation Methods

The growing complexity of machine learning and deep learning models has led to an increased reliance on opaque "black box" systems, making it difficult to understand the rationale behind predictions. This lack of transparency is particularly challenging in high-stakes applications where interpretability is as important as accuracy. Post-hoc explanation methods are commonly used to interpret these models, but they are seldom rigorously evaluated, raising concerns about their reliability. The Python package xai_evals addresses this by providing a comprehensive framework for generating, benchmarking, and evaluating explanation methods across both tabular and image data modalities. It integrates popular techniques like SHAP, LIME, Grad-CAM, Integrated Gradients (IG), and Backtrace, while supporting evaluation metrics such as faithfulness, sensitivity, and robustness. xai_evals enhances the interpretability of machine learning models, fostering transparency and trust in AI systems. The library is open-sourced at https://pypi.org/project/xai-evals/ .