When AI Persuades: Adversarial Explanation Attacks on Human Trust in AI-Assisted Decision Makingcs.AI updates on arXiv.org arXiv:2602.04003v1 Announce Type: new
Abstract: Most adversarial threats in artificial intelligence target the computational behavior of models rather than the humans who rely on them. Yet modern AI systems increasingly operate within human decision loops, where users interpret and act on model recommendations. Large Language Models generate fluent natural-language explanations that shape how users perceive and trust AI outputs, revealing a new attack surface at the cognitive layer: the communication channel between AI and its users. We introduce adversarial explanation attacks (AEAs), where an attacker manipulates the framing of LLM-generated explanations to modulate human trust in incorrect outputs. We formalize this behavioral threat through the trust miscalibration gap, a metric that captures the difference in human trust between correct and incorrect outputs under adversarial explanations. By incorporating this gap, AEAs explore the daunting threats in which persuasive explanations reinforce users’ trust in incorrect predictions. To characterize this threat, we conducted a controlled experiment (n = 205), systematically varying four dimensions of explanation framing: reasoning mode, evidence type, communication style, and presentation format. Our findings show that users report nearly identical trust for adversarial and benign explanations, with adversarial explanations preserving the vast majority of benign trust despite being incorrect. The most vulnerable cases arise when AEAs closely resemble expert communication, combining authoritative evidence, neutral tone, and domain-appropriate reasoning. Vulnerability is highest on hard tasks, in fact-driven domains, and among participants who are less formally educated, younger, or highly trusting of AI. This is the first systematic security study that treats explanations as an adversarial cognitive channel and quantifies their impact on human trust in AI-assisted decision making.
arXiv:2602.04003v1 Announce Type: new
Abstract: Most adversarial threats in artificial intelligence target the computational behavior of models rather than the humans who rely on them. Yet modern AI systems increasingly operate within human decision loops, where users interpret and act on model recommendations. Large Language Models generate fluent natural-language explanations that shape how users perceive and trust AI outputs, revealing a new attack surface at the cognitive layer: the communication channel between AI and its users. We introduce adversarial explanation attacks (AEAs), where an attacker manipulates the framing of LLM-generated explanations to modulate human trust in incorrect outputs. We formalize this behavioral threat through the trust miscalibration gap, a metric that captures the difference in human trust between correct and incorrect outputs under adversarial explanations. By incorporating this gap, AEAs explore the daunting threats in which persuasive explanations reinforce users’ trust in incorrect predictions. To characterize this threat, we conducted a controlled experiment (n = 205), systematically varying four dimensions of explanation framing: reasoning mode, evidence type, communication style, and presentation format. Our findings show that users report nearly identical trust for adversarial and benign explanations, with adversarial explanations preserving the vast majority of benign trust despite being incorrect. The most vulnerable cases arise when AEAs closely resemble expert communication, combining authoritative evidence, neutral tone, and domain-appropriate reasoning. Vulnerability is highest on hard tasks, in fact-driven domains, and among participants who are less formally educated, younger, or highly trusting of AI. This is the first systematic security study that treats explanations as an adversarial cognitive channel and quantifies their impact on human trust in AI-assisted decision making. Read More
GPT-5 lowers the cost of cell-free protein synthesisOpenAI News An autonomous lab combining OpenAI’s GPT-5 with Ginkgo Bioworks’ cloud automation cut cell-free protein synthesis costs by 40% through closed-loop experimentation.
An autonomous lab combining OpenAI’s GPT-5 with Ginkgo Bioworks’ cloud automation cut cell-free protein synthesis costs by 40% through closed-loop experimentation. Read More
AI Expo 2026 Day 2: Moving experimental pilots to AI productionAI News The second day of the co-located AI & Big Data Expo and Digital Transformation Week in London showed a market in a clear transition. Early excitement over generative models is fading. Enterprise leaders now face the friction of fitting these tools into current stacks. Day two sessions focused less on large language models and more
The post AI Expo 2026 Day 2: Moving experimental pilots to AI production appeared first on AI News.
The second day of the co-located AI & Big Data Expo and Digital Transformation Week in London showed a market in a clear transition. Early excitement over generative models is fading. Enterprise leaders now face the friction of fitting these tools into current stacks. Day two sessions focused less on large language models and more
The post AI Expo 2026 Day 2: Moving experimental pilots to AI production appeared first on AI News. Read More
OpenAI Just Launched GPT-5.3-Codex: A Faster Agentic Coding Model Unifying Frontier Code Performance And Professional Reasoning Into One SystemMarkTechPost OpenAI has just introduced GPT-5.3-Codex, a new agentic coding model that extends Codex from writing and reviewing code to handling a broad range of work on a computer. The model combines the frontier coding performance of GPT-5.2-Codex with the reasoning and professional knowledge capabilities of GPT-5.2 into a single system, and it runs 25% faster
The post OpenAI Just Launched GPT-5.3-Codex: A Faster Agentic Coding Model Unifying Frontier Code Performance And Professional Reasoning Into One System appeared first on MarkTechPost.
OpenAI has just introduced GPT-5.3-Codex, a new agentic coding model that extends Codex from writing and reviewing code to handling a broad range of work on a computer. The model combines the frontier coding performance of GPT-5.2-Codex with the reasoning and professional knowledge capabilities of GPT-5.2 into a single system, and it runs 25% faster
The post OpenAI Just Launched GPT-5.3-Codex: A Faster Agentic Coding Model Unifying Frontier Code Performance And Professional Reasoning Into One System appeared first on MarkTechPost. Read More
How to Build Production-Grade Data Validation Pipelines Using Pandera, Typed Schemas, and Composable DataFrame ContractsMarkTechPost Schemas, and Composable DataFrame ContractsIn this tutorial, we demonstrate how to build robust, production-grade data validation pipelines using Pandera with typed DataFrame models. We start by simulating realistic, imperfect transactional data and progressively enforce strict schema constraints, column-level rules, and cross-column business logic using declarative checks. We show how lazy validation helps us surface multiple
The post How to Build Production-Grade Data Validation Pipelines Using Pandera, Typed Schemas, and Composable DataFrame Contracts appeared first on MarkTechPost.
Schemas, and Composable DataFrame ContractsIn this tutorial, we demonstrate how to build robust, production-grade data validation pipelines using Pandera with typed DataFrame models. We start by simulating realistic, imperfect transactional data and progressively enforce strict schema constraints, column-level rules, and cross-column business logic using declarative checks. We show how lazy validation helps us surface multiple
The post How to Build Production-Grade Data Validation Pipelines Using Pandera, Typed Schemas, and Composable DataFrame Contracts appeared first on MarkTechPost. Read More
How Associa transforms document classification with the GenAI IDP Accelerator and Amazon BedrockArtificial Intelligence Associa collaborated with the AWS Generative AI Innovation Center to build a generative AI-powered document classification system aligning with Associa’s long-term vision of using generative AI to achieve operational efficiencies in document management. The solution automatically categorizes incoming documents with high accuracy, processes documents efficiently, and provides substantial cost savings while maintaining operational excellence. The document classification system, developed using the Generative AI Intelligent Document Processing (GenAI IDP) Accelerator, is designed to integrate seamlessly into existing workflows. It revolutionizes how employees interact with document management systems by reducing the time spent on manual classification tasks.
Associa collaborated with the AWS Generative AI Innovation Center to build a generative AI-powered document classification system aligning with Associa’s long-term vision of using generative AI to achieve operational efficiencies in document management. The solution automatically categorizes incoming documents with high accuracy, processes documents efficiently, and provides substantial cost savings while maintaining operational excellence. The document classification system, developed using the Generative AI Intelligent Document Processing (GenAI IDP) Accelerator, is designed to integrate seamlessly into existing workflows. It revolutionizes how employees interact with document management systems by reducing the time spent on manual classification tasks. Read More
A practical guide to Amazon Nova Multimodal EmbeddingsArtificial Intelligence In this post, you will learn how to configure and use Amazon Nova Multimodal Embeddings for media asset search systems, product discovery experiences, and document retrieval applications.
In this post, you will learn how to configure and use Amazon Nova Multimodal Embeddings for media asset search systems, product discovery experiences, and document retrieval applications. Read More
Anthropic Releases Claude Opus 4.6 With 1M Context, Agentic Coding, Adaptive Reasoning Controls, and Expanded Safety Tooling CapabilitiesMarkTechPost Anthropic has launched Claude Opus 4.6, its most capable model to date, focused on long-context reasoning, agentic coding, and high-value knowledge work. The model builds on Claude Opus 4.5 and is now available on claude.ai, the Claude API, and major cloud providers under the ID claude-opus-4-6. Model focus: agentic work, not single answers Opus 4.6
The post Anthropic Releases Claude Opus 4.6 With 1M Context, Agentic Coding, Adaptive Reasoning Controls, and Expanded Safety Tooling Capabilities appeared first on MarkTechPost.
Anthropic has launched Claude Opus 4.6, its most capable model to date, focused on long-context reasoning, agentic coding, and high-value knowledge work. The model builds on Claude Opus 4.5 and is now available on claude.ai, the Claude API, and major cloud providers under the ID claude-opus-4-6. Model focus: agentic work, not single answers Opus 4.6
The post Anthropic Releases Claude Opus 4.6 With 1M Context, Agentic Coding, Adaptive Reasoning Controls, and Expanded Safety Tooling Capabilities appeared first on MarkTechPost. Read More
Scaling In-Context Online Learning Capability of LLMs via Cross-Episode Meta-RLcs.AI updates on arXiv.org arXiv:2602.04089v1 Announce Type: new
Abstract: Large language models (LLMs) achieve strong performance when all task-relevant information is available upfront, as in static prediction and instruction-following problems. However, many real-world decision-making tasks are inherently online: crucial information must be acquired through interaction, feedback is delayed, and effective behavior requires balancing information collection and exploitation over time. While in-context learning enables adaptation without weight updates, existing LLMs often struggle to reliably leverage in-context interaction experience in such settings. In this work, we show that this limitation can be addressed through training. We introduce ORBIT, a multi-task, multi-episode meta-reinforcement learning framework that trains LLMs to learn from interaction in context. After meta-training, a relatively small open-source model (Qwen3-14B) demonstrates substantially improved in-context online learning on entirely unseen environments, matching the performance of GPT-5.2 and outperforming standard RL fine-tuning by a large margin. Scaling experiments further reveal consistent gains with model size, suggesting significant headroom for learn-at-inference-time decision-making agents. Code reproducing the results in the paper can be found at https://github.com/XiaofengLin7/ORBIT.
arXiv:2602.04089v1 Announce Type: new
Abstract: Large language models (LLMs) achieve strong performance when all task-relevant information is available upfront, as in static prediction and instruction-following problems. However, many real-world decision-making tasks are inherently online: crucial information must be acquired through interaction, feedback is delayed, and effective behavior requires balancing information collection and exploitation over time. While in-context learning enables adaptation without weight updates, existing LLMs often struggle to reliably leverage in-context interaction experience in such settings. In this work, we show that this limitation can be addressed through training. We introduce ORBIT, a multi-task, multi-episode meta-reinforcement learning framework that trains LLMs to learn from interaction in context. After meta-training, a relatively small open-source model (Qwen3-14B) demonstrates substantially improved in-context online learning on entirely unseen environments, matching the performance of GPT-5.2 and outperforming standard RL fine-tuning by a large margin. Scaling experiments further reveal consistent gains with model size, suggesting significant headroom for learn-at-inference-time decision-making agents. Code reproducing the results in the paper can be found at https://github.com/XiaofengLin7/ORBIT. Read More
A Novel Framework for Uncertainty-Driven Adaptive Explorationcs.AI updates on arXiv.org arXiv:2509.03219v5 Announce Type: replace
Abstract: Adaptive exploration methods propose ways to learn complex policies via alternating between exploration and exploitation. An important question for such methods is to determine the appropriate moment to switch between exploration and exploitation and vice versa. This is critical in domains that require the learning of long and complex sequences of actions. In this work, we present a generic adaptive exploration framework that employs uncertainty to address this important issue in a principled manner. Our framework includes previous adaptive exploration approaches as special cases. Moreover, we can incorporate in our framework any uncertainty-measuring mechanism of choice, for instance mechanisms used in intrinsic motivation or epistemic uncertainty-based exploration methods. We experimentally demonstrate that our framework gives rise to adaptive exploration strategies that outperform standard ones across several environments.
arXiv:2509.03219v5 Announce Type: replace
Abstract: Adaptive exploration methods propose ways to learn complex policies via alternating between exploration and exploitation. An important question for such methods is to determine the appropriate moment to switch between exploration and exploitation and vice versa. This is critical in domains that require the learning of long and complex sequences of actions. In this work, we present a generic adaptive exploration framework that employs uncertainty to address this important issue in a principled manner. Our framework includes previous adaptive exploration approaches as special cases. Moreover, we can incorporate in our framework any uncertainty-measuring mechanism of choice, for instance mechanisms used in intrinsic motivation or epistemic uncertainty-based exploration methods. We experimentally demonstrate that our framework gives rise to adaptive exploration strategies that outperform standard ones across several environments. Read More