Recent developments in Artificial Intelligence (AI) and their applications in critical industries such as healthcare, fin-tech and cybersecurity have led to a surge in research in explainability in AI. Innovative research methods are being explored to extract meaningful insight from blackbox AI systems to make the decision-making technology transparent and interpretable. Explainability becomes all the more critical when AI is used in decision making in domains like fintech, healthcare and safety critical systems such as cybersecurity and autonomous vehicles. However, there is still ambiguity lingering on the reliable evaluations for the users and nature of transparency in the explanations provided for the decisions made by black-boxed AI. To solve the blackbox nature of Machine Learning based Intrusion Detection Systems, a framework is proposed in this paper to give an explanation for IDSs decision making. This framework uses Local Interpretable Model-Agnostic Explanations (LIME) coupled with Explain Like I'm five (ELI5) and Decision Tree algorithms to provide local and global explanations and improve the interpretation of IDSs. The local explanations provide the justification for the decision made on a specific input. Whereas, the global explanations provides the list of significant features and their relationship with attack traffic. In addition, this framework brings transparency in the field of ML driven IDS that might be highly significant for wide scale adoption of eXplainable AI in cyber-critical systems. Our framework is able to achieve 85 percent accuracy in classifying attack behaviour on UNSW-NB15 dataset, while at the same time displaying the feature significance ranking of the top 10 features used in the classification.

Retrieval-Augmented Generation (RAG) is a powerful technique for enhancing Large Language Models (LLMs) with external, up-to-date knowledge. Graph RAG has emerged as an advanced paradigm that leverages graph-based knowledge structures to provide more coherent and contextually rich answers. However, the move from plain document retrieval to structured graph traversal introduces new, under-explored privacy risks. This paper investigates the data extraction vulnerabilities of the Graph RAG systems. We design and execute tailored data extraction attacks to probe their susceptibility to leaking both raw text and structured data, such as entities and their relationships. Our findings reveal a critical trade-off: while Graph RAG systems may reduce raw text leakage, they are significantly more vulnerable to the extraction of structured entity and relationship information. We also explore potential defense mechanisms to mitigate these novel attack surfaces. This work provides a foundational analysis of the unique privacy challenges in Graph RAG and offers insights for building more secure systems.

This paper introduces a multi-agent framework for comprehensive highway scene understanding, designed around a mixture-of-experts strategy. In this framework, a large generic vision-language model (VLM), such as GPT-4o, is contextualized with domain knowledge to generates task-specific chain-of-thought (CoT) prompts. These fine-grained prompts are then used to guide a smaller, efficient VLM (e.g., Qwen2.5-VL-7B) in reasoning over short videos, along with complementary modalities as applicable. The framework simultaneously addresses multiple critical perception tasks, including weather classification, pavement wetness assessment, and traffic congestion detection, achieving robust multi-task reasoning while balancing accuracy and computational efficiency. To support empirical validation, we curated three specialized datasets aligned with these tasks. Notably, the pavement wetness dataset is multimodal, combining video streams with road weather sensor data, highlighting the benefits of multimodal reasoning. Experimental results demonstrate consistently strong performance across diverse traffic and environmental conditions. From a deployment perspective, the framework can be readily integrated with existing traffic camera systems and strategically applied to high-risk rural locations, such as sharp curves, flood-prone lowlands, or icy bridges. By continuously monitoring the targeted sites, the system enhances situational awareness and delivers timely alerts, even in resource-constrained environments.

In this work, we explore the capability of Large Language Models (LLMs) to annotate hate speech and abusiveness while considering predefined annotator personas within the strong-to-weak data perspectivism spectra. We evaluated LLM-generated annotations against existing annotator modeling techniques for perspective modeling. Our findings show that LLMs selectively use demographic attributes from the personas. We identified prototypical annotators, with persona features that show varying degrees of alignment with the original human annotators. Within the data perspectivism paradigm, annotator modeling techniques that do not explicitly rely on annotator information performed better under weak data perspectivism compared to both strong data perspectivism and human annotations, suggesting LLM-generated views tend towards aggregation despite subjective prompting. However, for more personalized datasets tailored to strong perspectivism, the performance of LLM annotator modeling approached, but did not exceed, human annotators.

Large language model fine-tuning APIs enable widespread model customization, yet pose significant safety risks. Recent work shows that adversaries can exploit access to these APIs to bypass model safety mechanisms by encoding harmful content in seemingly harmless fine-tuning data, evading both human monitoring and standard content filters. We formalize the fine-tuning API defense problem, and introduce the Cipher Fine-tuning Robustness benchmark (CIFR), a benchmark for evaluating defense strategies' ability to retain model safety in the face of cipher-enabled attackers while achieving the desired level of fine-tuning functionality. We include diverse cipher encodings and families, with some kept exclusively in the test set to evaluate for generalization across unseen ciphers and cipher families. We then evaluate different defenses on the benchmark and train probe monitors on model internal activations from multiple fine-tunes. We show that probe monitors achieve over 99% detection accuracy, generalize to unseen cipher variants and families, and compare favorably to state-of-the-art monitoring approaches. We open-source CIFR and the code to reproduce our experiments to facilitate further research in this critical area. Code and data are available online https://github.com/JackYoustra/safe-finetuning-api

Punishment as a mechanism for promoting cooperation has been studied extensively for more than two decades, but its effectiveness remains a matter of dispute. Here, we examine how punishment's impact varies across cooperative settings through a large-scale integrative experiment. We vary 14 parameters that characterize public goods games, sampling 360 experimental conditions and collecting 147,618 decisions from 7,100 participants. Our results reveal striking heterogeneity in punishment effectiveness: while punishment consistently increases contributions, its impact on payoffs (i.e., efficiency) ranges from dramatically enhancing welfare (up to 43% improvement) to severely undermining it (up to 44% reduction) depending on the cooperative context. To characterize these patterns, we developed models that outperformed human forecasters (laypeople and domain experts) in predicting punishment outcomes in new experiments. Communication emerged as the most predictive feature, followed by contribution framing (opt-out vs. opt-in), contribution type (variable vs. all-or-nothing), game length (number of rounds), peer outcome visibility (whether participants can see others' earnings), and the availability of a reward mechanism. Interestingly, however, most of these features interact to influence punishment effectiveness rather than operating independently. For example, the extent to which longer games increase the effectiveness of punishment depends on whether groups can communicate. Together, our results refocus the debate over punishment from whether or not it "works" to the specific conditions under which it does and does not work. More broadly, our study demonstrates how integrative experiments can be combined with machine learning to uncover generalizable patterns, potentially involving interactions between multiple features, and help generate novel explanations in complex social phenomena.

Search engines play a central role in how people gather information, but subtle cues like headline framing may influence not only what users believe but also how they search. While framing effects on judgment are well documented, their impact on subsequent search behavior is less understood. We conducted a controlled experiment where participants issued queries and selected from headlines filtered by specific linguistic frames. Headline framing significantly shaped follow-up queries: conflict and strategy frames disrupted alignment with prior selections, while episodic frames led to more concrete queries than thematic ones. We also observed modest short-term frame persistence that declined over time. These results suggest that even brief exposure to framing can meaningfully alter the direction of users information-seeking behavior.

We address the problem of data scarcity in harmful text classification for guardrailing applications and introduce GRAID (Geometric and Reflective AI-Driven Data Augmentation), a novel pipeline that leverages Large Language Models (LLMs) for dataset augmentation. GRAID consists of two stages: (i) generation of geometrically controlled examples using a constrained LLM, and (ii) augmentation through a multi-agentic reflective process that promotes stylistic diversity and uncovers edge cases. This combination enables both reliable coverage of the input space and nuanced exploration of harmful content. Using two benchmark data sets, we demonstrate that augmenting a harmful text classification dataset with GRAID leads to significant improvements in downstream guardrail model performance.

AI Alignment, primarily in the form of Reinforcement Learning from Human Feedback (RLHF), has been a cornerstone of the post-training phase in developing Large Language Models (LLMs). It has also been a popular research topic across various disciplines beyond Computer Science, including Philosophy and Law, among others, highlighting the socio-technical challenges involved. Nonetheless, except for the computational techniques related to alignment, there has been limited focus on the broader picture: the scope of these processes, which primarily rely on the selected objectives (values), and the data collected and used to imprint such objectives into the models. This work aims to reveal how alignment is understood and applied in practice from a value-setting and data-centric perspective. For this purpose, we investigate and survey (`audit') publicly available documentation released by 6 LLM development initiatives by 5 leading organizations shaping this technology, focusing on proprietary (OpenAI's GPT, Anthropic's Claude, Google's Gemini) and open-weight (Meta's Llama, Google's Gemma, and Alibaba's Qwen) initiatives, all published in the last 3 years. The findings are documented in detail per initiative, while there is also an overall summary concerning different aspects, mainly from a value-setting and data-centric perspective. On the basis of our findings, we discuss a series of broader related concerns.

Large and Transformer-based language models perform outstandingly in various downstream tasks. However, there is limited understanding regarding how these models internalize linguistic knowledge, so various linguistic benchmarks have recently been proposed to facilitate syntactic evaluation of language models across languages. This paper introduces QFrCoLA (Quebec-French Corpus of Linguistic Acceptability Judgments), a normative binary acceptability judgments dataset comprising 25,153 in-domain and 2,675 out-of-domain sentences. Our study leverages the QFrCoLA dataset and seven other linguistic binary acceptability judgment corpora to benchmark seven language models. The results demonstrate that, on average, fine-tuned Transformer-based LM are strong baselines for most languages and that zero-shot binary classification large language models perform poorly on the task. However, for the QFrCoLA benchmark, on average, a fine-tuned Transformer-based LM outperformed other methods tested. It also shows that pre-trained cross-lingual LLMs selected for our experimentation do not seem to have acquired linguistic judgment capabilities during their pre-training for Quebec French. Finally, our experiment results on QFrCoLA show that our dataset, built from examples that illustrate linguistic norms rather than speakers' feelings, is similar to linguistic acceptability judgment; it is a challenging dataset that can benchmark LM on their linguistic judgment capabilities.