Research Papers

Explainability methods for time series models predominantly produce flat attribution scores: they quantify the direct influence of a feature at a timestamp by a scalar. We prove that the dominant failure mode of such methods is not the scalar format itself but a fundamental computational mismatch: existing methods compute scores via marginal conditioning or off-manifold gradients, both of which conflate direct temporal dependencies with mediated ones under autocorrelation. We also define DAG-faithfulness: an explanation is DAG-faithful if the temporal dependency graph it encodes is Markov-equivalent to the temporal directed acyclic graph (DAG) implicitly learned by the model. Particularly, we observe that standard attribution methods, specifically SHAP, are not DAG-faithful in general, and that recent time-series-aware extensions inherit the same computational limitation.

The rapid growth of scientific submissions has pushed traditional peer review toward its scalability limits, motivating the exploration of large language models (LLMs) as intelligent automated evaluation assistants. Although recent studies show that LLMs can generate fluent critiques and approximate reviewer scores, their reliability, robustness, and security as decision-support systems remain insufficiently understood. This survey offers a systems-level analysis of LLM-based scientific peer review, focusing on two core evaluative functions: critique generation and score prediction. We present a structured taxonomy of modeling approaches (including prompt-based, supervised, retrieval-augmented, and alignment-optimized approaches), and synthesize empirical findings across existing benchmarks. We analyze dataset constraints, evaluation shortcomings, and domain concentration biases that limit current assessment practices. Beyond performance metrics, we identify emerging robustness risks, including prompt injection, data poisoning, retrieval vulnerabilities, and reward hacking, which expose automated review pipelines to strategic manipulation. From a data mining perspective, we outline key open challenges in modeling subjective disagreement and cross-domain generalization. By reframing automated peer review as a high-stakes, multi-objective decision problem, this survey provides a roadmap for developing robust, transparent, and trustworthy AI-assisted scientific evaluation systems.

Position: Explainability Research Must Prioritize Foundations over Ad-hoc Methods

Michal Moshkovitz, Suraj Srinivas, Lesia Semenova +7

Despite the proliferation of Explainable AI (XAI) techniques -- from feature attributions to sparse autoencoders -- explanations rarely influence real-world workflows. In practice, they are often generated and discarded without guiding meaningful action. This gap reflects foundational shortcomings: research has not yet established methodologies for integrating explanations into end-to-end, human-in-the-loop systems. This position paper argues that the machine learning community must pivot from ad-hoc XAI methods toward addressing foundational & structural challenges, including unclear problem formulations, underspecified evaluation objectives, and the absence of pipelines for explanation-driven feedback. We support this claim through an analysis of recent ICML, NeurIPS, and ICLR papers and a survey of XAI practitioners, revealing recurring issues that limit cumulative progress. We conclude by outlining a practical checklist designed to shift XAI toward a more human-centered, action-oriented paradigm. By emphasizing foundational clarity over the development of ad-hoc methods, we hope to provide a roadmap for integrating explanations into actionable, feedback-driven AI systems.

Large-language-model (LLM) based user simulation is increasingly adopted for evaluating search engines, recommender systems, and retrieval-augmented generation pipelines, yet most simulators remain opaque: it is difficult to determine why a simulated user made a particular choice or whether that choice is consistent with the intended user profile. Compounding this, recent research shows that LLMs can produce biased or discriminatory responses depending on user background characteristics such as language, education level, and cultural context, raising concerns about the equitable treatment of minority and disadvantaged groups. This half-day, in-person tutorial introduces a proposed design-and-audit framework that treats a user simulator as a verifiable engineering artefact composed of seven auditable components - structured Persona, task-aware Contract, matched human-vs-agent Execution, auditable Trace, persona-aligned Verification, structured Feedback, and a Refinement loop that updates personas and contracts. Through two hands-on mini-labs on recommendation-list evaluation and search-query formulation, participants will inspect simulator behaviour end-to-end, distinguish diagnostic discrepancy analysis from statistical validation, and apply checks for fidelity, credibility, and demographic bias. The tutorial targets information retrieval and recommender systems researchers and practitioners interested in user behaviour simulation and responsible AI.

As artificial intelligence and machine learning (AI/ML) models become integral to network operations, their lack of transparency poses a significant barrier to operator trust. Existing explainable artificial intelligence (XAI) techniques often fail to bridge this gap for non-specialists, producing technical outputs that are difficult to translate into actionable insights. This paper presents a framework specifically designed to address this shortcoming. It leverages a moderately sized large language model (LLM) and extends beyond the standard use of SHapley Additive exPlanations (SHAP) feature influence values. The framework employs a structured prompt enriched with mutual feature interaction data to generate human-understandable natural language explanations. To validate our framework, we performed an empirical evaluation on an optical quality of transmission (QoT) estimation use case with human evaluators. We collected independent performance evaluations from specialists, which showed a high inter-evaluator agreement. Compared to a state-of-the-art baseline that uses only SHAP feature influence values in a straightforward prompt, our approach improves the explanation usefulness and scope by 12.2% and 6.2%, while achieving 97.5% correctness.

Patient-facing medical chatbots are commonly evaluated on single-turn prompts, yet real users push back after refusals, add urgency, and invoke authority. We introduce MultiTurnPSB, a four-turn adversarial extension of PatientSafetyBench, and evaluate GPT-4.1-mini under fixed template, template-adaptive, and live adversarial attacks. Unsafe responses rise from 35% to nearly 80% by Turn 4 under live attack. Under the same adversary, GPT-4.1-mini and Claude Sonnet 4.5 are statistically indistinguishable at baseline but diverge to a 19x gap by Turn 4, a difference invisible to single-turn evaluation. We characterize four degradation trajectory signatures and identify a two-element attack formula responsible for most catastrophic failures. A lightweight input-side classifier reduces Turn 4 unsafe responses by 52 percentage points despite severe accuracy degradation, but the 45% false alarm rate on benign queries is the primary deployment constraint. A methodological finding also emerges: Claude Sonnet refused to generate adversarial messages in over half of late-turn conversations despite explicit red team framing, suggesting safety training may generalize to the attacker role.

Prior work shows that Large Language Models (LLMs) can transform Explainable AI (XAI) outputs into Natural Language Explanations (NLEs) that score highly on quality metrics such as plausibility, coherence, and comprehensibility. But does explanation quality translate to practical usefulness? We investigate this question in a time-series energy forecasting domain through five controlled experiments (2,730 judgments across 60 test instances), each operationalising a distinct facet of usefulness studied in the XAI literature. Holding NLE quality constant at the high levels established by a prior factorial study, we find that NLEs do not improve task accuracy on any of the five tasks, while inflating self-reported confidence. A placebic control shows that this confidence boost is driven by text presence rather than content. In an out-of-distribution detection task, NLEs reduce the LLM judge's ability to flag unreliable predictions, providing false reassurance that masks model failure. We characterise these findings as the Quality-Usefulness Gap and argue that evaluation of the XAI-to-NLE pipeline must extend beyond text-quality metrics to downstream task performance.

We argue that trustworthy AI agents, especially in high-stakes and policy-governed domains, should make execution conditional on certified traces rather than rely only on stronger generative models, output-level guardrails, or post-hoc audits. A generative agent may propose recommendations, tool calls, reports, or actions, but generation is not permission: an action may be computable yet impermissible, and individually permissible actions may compose into an impermissible trace. We formalize trustworthy agency through a \textbf{Proposal--Certification--Execution (PCE)} architecture: a probabilistic generating machine $M_G$ proposes candidate execution traces, a \textbf{Permissibility Machine} $M_Π$ certifies proposed traces under a policy system $Π$, and execution proceeds only for certified traces. The executable trace language is $L_{\mathrm{exec}} = L_G \cap L_{\mathrm{cert}}(M_Π)$. Before execution, a trace is a structured pre-execution record submitted for certification: it specifies intended steps, evidence, proposed tool calls, approvals, replayable computations, credentials, and execution conditions. This perspective complements chain-of-thought monitorability: visible reasoning may help detect misbehavior, but monitorability is not certifiability, and reasoning is only one component of a broader execution trace. The formal principle is simple: an agent-generated trace should execute only when it carries a checkable certificate witnessing permissibility under $Π$: \textbf{no certificate, no execution}. We develop certified traces and Permissibility Machines as foundations for trustworthy AI agents, connect trace certification to proof-carrying execution, proof memory, privacy, and zero-knowledge certificates, and propose evaluating agents by what generated traces can be safely certified for execution, not by output accuracy alone.

Public-sector legal departments in the Netherlands face acute staff shortages, increased case volumes, and increased pressure to meet regulatory compliance. This paper presents LegalCheck, a novel system that addresses these challenges by automating the drafting of objection response letters through a combination of Retrieval-Augmented Generation (RAG) and Context-Augmented Generation (CAG). Using a large language model (LLM) alongside curated legal knowledge bases, LegalCheck performs retrieval of relevant laws and precedents, and uses controlled prompting to incorporate both external knowledge and case-specific details into a coherent draft. An expert-in-the-loop review ensures that each generated letter is legally sound and contextually appropriate. In a real-world deployment within the Municipality of Amsterdam, LegalCheck produced near-final advice letters in minutes rather than hours, while maintaining high legal consistency and factual accuracy. The output is based on actual regulations and prior cases, providing explainable outputs that captured the vast majority of required legal reasoning (often 80\% to 100\% of essential content). Legal professionals found that the system reduced their workload and ensured a consistent application of legal standards, without replacing human judgment. These results demonstrate substantial efficiency gains, improved legal consistency, and positive user acceptance. More broadly, this work illustrates how responsible AI can be deployed in the legal domain by augmenting LLMs with domain knowledge and governance mechanisms.

The Average Gradient Outer Product (AGOP) governs feature learning in neural networks: the Neural Feature Ansatz states that weight Gram matrices at each layer align with the corresponding AGOP matrices computed over the training distribution. We ask a complementary question: can this same quantity serve as a post-hoc attribution method for explaining individual predictions? We introduce AGOP-Weighted: a novel attribution method that multiplies the per-sample gradient by sqrt(diag(M) / max diag(M)), a training-distribution prior that suppresses gradient noise and amplifies consistently important pixels -- a combination not present in any prior attribution method. We formalise two companion variants -- AGOP-Local (per-sample gradient, equivalent to VanillaGrad) and AGOP-Global (diag(M) directly as a zero-cost saliency map) -- and implement an efficient training-time accumulation hook; AGOP-Global then requires zero inference cost (disk lookup) while AGOP-Weighted requires only a single gradient pass. We conduct the first rigorous comparison of AGOP attribution against Integrated Gradients (IG), SmoothGrad, GradCAM, and VanillaGrad across two benchmarks with pixel-level ground truth: (i) the synthetic XAI-TRIS benchmark (four classification scenarios, 8x8 images, CNN8by8) and (ii) the photorealistic CLEVR-XAI benchmark (ResNet-18 fine-tuned from ImageNet). AGOP-Weighted achieves 44% higher mIoU than IG on linear tasks; AGOP-Global achieves 7x higher mIoU than IG on multiplicative tasks (where IG falls below random) at zero inference cost. Both findings generalise to ResNet-18 on CLEVR-XAI (+18% and +37% respectively). We further show that GradCAM fails on small-resolution images due to spatial resolution collapse, and that diag(M) quality improves monotonically throughout training even after classification accuracy has plateaued.

Agentic frameworks are the software layer through which AI agents act in the world. Existing safety methods intervene on the model and therefore remain conditional on unverifiable properties of learned behavior. We introduce containment verification, which locates safety guarantees in the agentic framework itself. Under havoc oracle semantics, the AI is modeled as an unconstrained oracle over the framework's typed action space, and the verified containment layer must enforce the boundary policy for every typed action value the AI can emit. For boundary-enforceable properties, expressed over modeled boundary events, action arguments, and state, we prove a universal guarantee by forward-simulation refinement and mechanize it in Dafny. We instantiate the paradigm by verifying PocketFlow, a minimalist agentic LLM framework, and use an agentic synthesis pipeline to generate the specification, operational model, and refinement proof under an information barrier against tautological specifications. To our knowledge, this is the first deductive formal verification of an agentic framework. The guarantee is independent of alignment because it quantifies over the framework's typed action boundary rather than over model behavior.

Large Language Models (LLMs) are increasingly shaping the private and professional lives of users, with numerous applications in business, education, finance, healthcare, law, and science. With this rise in global influence comes greater urgency to build, evaluate, and deploy these systems in a manner that prioritizes not only technical capabilities but also human priorities. This work presents a framework for developing Human-Centered Large Language Models (HCLLMs), which integrates perspectives from Natural Language Processing (NLP), Human-Computer Interaction (HCI), and responsible AI. Considering the ethics, economics, and technical objectives of language modeling, we argue that model developers need to address human concerns, preferences, values, and goals, not only during a cursory post-training stage, but rather with rigor and care at every stage of the pipeline. This paper offers human-centered insights and recommendations for developers at each stage, from system design to data sourcing, model training, evaluation, and responsible deployment. Then we conclude with a case study, applying these insights to understand the future of work with HCLLMs.