Towards Effectively Leveraging Execution Traces for Program Repair with Code LLMs

Large Language Models (LLMs) show promising performance on various programming tasks, including Automatic Program Repair (APR). However, most approaches to LLM-based APR are limited to the static analysis of the programs, while disregarding their runtime behavior. Inspired by knowledge-augmented NLP, in this work, we aim to remedy this potential blind spot by augmenting standard APR prompts with program execution traces. We evaluate our approach using the GPT family of models on three popular APR datasets. Our findings suggest that simply incorporating execution traces into the prompt provides a limited performance improvement over trace-free baselines, in only 2 out of 6 tested dataset / model configurations. We further find that the effectiveness of execution traces for APR diminishes as their complexity increases. We explore several strategies for leveraging traces in prompts and demonstrate that LLM-optimized prompts help outperform trace-free prompts more consistently. Additionally, we show trace-based prompting to be superior to finetuning a smaller LLM on a small-scale dataset; and conduct probing studies reinforcing the notion that execution traces can complement the reasoning abilities of the LLMs.

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition

Knowledge distillation allows smaller neural networks to emulate the performance of larger, teacher models with reduced computational demands. Traditional methods for Large Language Models (LLMs) often necessitate extensive fine-tuning, which limits their accessibility. To address this, we introduce Trace-of-Thought Prompting, a novel framework designed to distill critical reasoning capabilities from high-resource teacher models (over 8 billion parameters) to low-resource student models (up to 8 billion parameters). This approach leverages problem decomposition to enhance interpretability and facilitate human-in-the-loop interventions. Empirical evaluations on the GSM8K and MATH datasets show that student models achieve accuracy gains of up to 113% on GSM8K and 21% on MATH, with significant improvements particularly notable in smaller models like Llama 2 and Zephyr. Our results suggest a promising pathway for open-source, low-resource models to eventually serve both as both students and teachers, potentially reducing our reliance on high-resource, proprietary models.

Efficient Quantum-Safe Homomorphic Encryption for Quantum Computer Programs

We present a lattice-based scheme for homomorphic evaluation of quantum programs and proofs that remains secure against quantum adversaries. Classical homomorphic encryption is lifted to the quantum setting by replacing composite-order groups with Module Learning-With-Errors (MLWE) lattices and by generalizing polynomial functors to bounded natural super functors (BNSFs). A secret depolarizing BNSF mask hides amplitudes, while each quantum state is stored as an MLWE ciphertext pair. We formalize security with the qIND-CPA game that allows coherent access to the encryption oracle and give a four-hybrid reduction to decisional MLWE. The design also covers practical issues usually left open. A typed QC-bridge keeps classical bits produced by measurements encrypted yet still usable as controls, with weak-measurement semantics for expectation-value workloads. Encrypted Pauli twirls add circuit privacy. If a fixed knowledge base is needed, its axioms are shipped as MLWE "capsules"; the evaluator can use them but cannot read them. A rho-calculus driver schedules encrypted tasks across several QPUs and records an auditable trace on an RChain-style ledger. Performance analysis shows that the extra lattice arithmetic fits inside today's QPU idle windows: a 100-qubit, depth-10^3 teleportation-based proof runs in about 10 ms, the public key (seed only) is 32 bytes, and even a CCA-level key stays below 300 kB. A photonic Dirac-3 prototype that executes homomorphic teleportation plus knowledge-base-relative amplitude checks appears feasible with current hardware. These results indicate that fully homomorphic, knowledge-base-aware quantum reasoning is compatible with near-term quantum clouds and standard post-quantum security assumptions.

Improving Deep Knowledge Tracing via Gated Architectures and Adaptive Optimization

Deep Knowledge Tracing (DKT) models student learning behavior by using Recurrent Neural Networks (RNNs) to predict future performance based on historical interaction data. However, the original implementation relied on standard RNNs in the Lua-based Torch framework, which limited extensibility and reproducibility. In this work, we revisit the DKT model from two perspectives: architectural improvements and optimization efficiency. First, we enhance the model using gated recurrent units, specifically Long Short-Term Memory (LSTM) networks and Gated Recurrent Units (GRU), which better capture long-term dependencies and help mitigate vanishing gradient issues. Second, we re-implement DKT using the PyTorch framework, enabling a modular and accessible infrastructure compatible with modern deep learning workflows. We also benchmark several optimization algorithms SGD, RMSProp, Adagrad, Adam, and AdamW to evaluate their impact on convergence speed and predictive accuracy in educational modeling tasks. Experiments on the Synthetic-5 and Khan Academy datasets show that GRUs and LSTMs achieve higher accuracy and improved training stability compared to basic RNNs, while adaptive optimizers such as Adam and AdamW consistently outperform SGD in both early-stage learning and final model performance. Our open-source PyTorch implementation provides a reproducible and extensible foundation for future research in neural knowledge tracing and personalized learning systems.

Survey of Loss Augmented Knowledge Tracing

The training of artificial neural networks is heavily dependent on the careful selection of an appropriate loss function. While commonly used loss functions, such as cross-entropy and mean squared error (MSE), generally suffice for a broad range of tasks, challenges often emerge due to limitations in data quality or inefficiencies within the learning process. In such circumstances, the integration of supplementary terms into the loss function can serve to address these challenges, enhancing both model performance and robustness. Two prominent techniques, loss regularization and contrastive learning, have been identified as effective strategies for augmenting the capacity of loss functions in artificial neural networks. Knowledge tracing is a compelling area of research that leverages predictive artificial intelligence to facilitate the automation of personalized and efficient educational experiences for students. In this paper, we provide a comprehensive review of the deep learning-based knowledge tracing (DKT) algorithms trained using advanced loss functions and discuss their improvements over prior techniques. We discuss contrastive knowledge tracing algorithms, such as Bi-CLKT, CL4KT, SP-CLKT, CoSKT, and prediction-consistent DKT, providing performance benchmarks and insights into real-world deployment challenges. The survey concludes with future research directions, including hybrid loss strategies and context-aware modeling.

Unified Attacks to Large Language Model Watermarks: Spoofing and Scrubbing in Unauthorized Knowledge Distillation

Watermarking has emerged as a critical technique for combating misinformation and protecting intellectual property in large language models (LLMs). A recent discovery, termed watermark radioactivity, reveals that watermarks embedded in teacher models can be inherited by student models through knowledge distillation. On the positive side, this inheritance allows for the detection of unauthorized knowledge distillation by identifying watermark traces in student models. However, the robustness of watermarks against scrubbing attacks and their unforgeability in the face of spoofing attacks under unauthorized knowledge distillation remain largely unexplored. Existing watermark attack methods either assume access to model internals or fail to simultaneously support both scrubbing and spoofing attacks. In this work, we propose Contrastive Decoding-Guided Knowledge Distillation (CDG-KD), a unified framework that enables bidirectional attacks under unauthorized knowledge distillation. Our approach employs contrastive decoding to extract corrupted or amplified watermark texts via comparing outputs from the student model and weakly watermarked references, followed by bidirectional distillation to train new student models capable of watermark removal and watermark forgery, respectively. Extensive experiments show that CDG-KD effectively performs attacks while preserving the general performance of the distilled model. Our findings underscore critical need for developing watermarking schemes that are robust and unforgeable.

AI Awareness

Recent breakthroughs in artificial intelligence (AI) have brought about increasingly capable systems that demonstrate remarkable abilities in reasoning, language understanding, and problem-solving. These advancements have prompted a renewed examination of AI awareness, not as a philosophical question of consciousness, but as a measurable, functional capacity. In this review, we explore the emerging landscape of AI awareness, which includes meta-cognition (the ability to represent and reason about its own state), self-awareness (recognizing its own identity, knowledge, limitations, inter alia), social awareness (modeling the knowledge, intentions, and behaviors of other agents), and situational awareness (assessing and responding to the context in which it operates). First, we draw on insights from cognitive science, psychology, and computational theory to trace the theoretical foundations of awareness and examine how the four distinct forms of AI awareness manifest in state-of-the-art AI. Next, we systematically analyze current evaluation methods and empirical findings to better understand these manifestations. Building on this, we explore how AI awareness is closely linked to AI capabilities, demonstrating that more aware AI agents tend to exhibit higher levels of intelligent behaviors. Finally, we discuss the risks associated with AI awareness, including key topics in AI safety, alignment, and broader ethical concerns. AI awareness is a double-edged sword: it improves general capabilities, i.e., reasoning, safety, while also raises concerns around misalignment and societal risks, demanding careful oversight as AI capabilities grow. On the whole, our interdisciplinary review provides a roadmap for future research and aims to clarify the role of AI awareness in the ongoing development of intelligent machines.

Adapting Probabilistic Risk Assessment for AI

Modern general-purpose artificial intelligence (AI) systems present an urgent risk management challenge, as their rapidly evolving capabilities and potential for catastrophic harm outpace our ability to reliably assess their risks. Current methods often rely on selective testing and undocumented assumptions about risk priorities, frequently failing to make a serious attempt at assessing the set of pathways through which Al systems pose direct or indirect risks to society and the biosphere. This paper introduces the probabilistic risk assessment (PRA) for AI framework, adapting established PRA techniques from high-reliability industries (e.g., nuclear power, aerospace) for the new challenges of advanced AI. The framework guides assessors in identifying potential risks, estimating likelihood and severity, and explicitly documenting evidence, underlying assumptions, and analyses at appropriate granularities. The framework's implementation tool synthesizes the results into a risk report card with aggregated risk estimates from all assessed risks. This systematic approach integrates three advances: (1) Aspect-oriented hazard analysis provides systematic hazard coverage guided by a first-principles taxonomy of AI system aspects (e.g. capabilities, domain knowledge, affordances); (2) Risk pathway modeling analyzes causal chains from system aspects to societal impacts using bidirectional analysis and incorporating prospective techniques; and (3) Uncertainty management employs scenario decomposition, reference scales, and explicit tracing protocols to structure credible projections with novelty or limited data. Additionally, the framework harmonizes diverse assessment methods by integrating evidence into comparable, quantified absolute risk estimates for critical decisions. We have implemented this as a workbook tool for AI developers, evaluators, and regulators, available on the project website.

Exploring How LLMs Capture and Represent Domain-Specific Knowledge

We study whether Large Language Models (LLMs) inherently capture domain-specific nuances in natural language. Our experiments probe the domain sensitivity of LLMs by examining their ability to distinguish queries from different domains using hidden states generated during the prefill phase. We reveal latent domain-related trajectories that indicate the model's internal recognition of query domains. We also study the robustness of these domain representations to variations in prompt styles and sources. Our approach leverages these representations for model selection, mapping the LLM that best matches the domain trace of the input query (i.e., the model with the highest performance on similar traces). Our findings show that LLMs can differentiate queries for related domains, and that the fine-tuned model is not always the most accurate. Unlike previous work, our interpretations apply to both closed and open-ended generative tasks

Verifying Robust Unlearning: Probing Residual Knowledge in Unlearned Models

Machine Unlearning (MUL) is crucial for privacy protection and content regulation, yet recent studies reveal that traces of forgotten information persist in unlearned models, enabling adversaries to resurface removed knowledge. Existing verification methods only confirm whether unlearning was executed, failing to detect such residual information leaks. To address this, we introduce the concept of Robust Unlearning, ensuring models are indistinguishable from retraining and resistant to adversarial recovery. To empirically evaluate whether unlearning techniques meet this security standard, we propose the Unlearning Mapping Attack (UMA), a post-unlearning verification framework that actively probes models for forgotten traces using adversarial queries. Extensive experiments on discriminative and generative tasks show that existing unlearning techniques remain vulnerable, even when passing existing verification metrics. By establishing UMA as a practical verification tool, this study sets a new standard for assessing and enhancing machine unlearning security.