Understanding Transparency in AI Outputs

AI explainability is critical for trust and accountability in AI systems. The report “AI Explainability in Practice” highlights key principles and practical steps to ensure AI decisions are transparent, fair, and understandable to diverse stakeholders. Key takeaways: • Explanations in AI can be process-based (how the system was designed and governed) or outcome-based (why a specific decision was made). Both are essential for trust. • Clear, accessible explanations should be tailored to stakeholders’ needs, including non-technical audiences and vulnerable groups such as children. • Transparency and accountability require documenting data sources, model selection, testing, and risk assessments to demonstrate fairness and safety. • Effective AI explainability includes providing rationale, responsibility, safety, fairness, data, and impact explanations. • Use interpretable models where possible, and when black-box models are necessary, supplement with interpretability tools to explain decisions at both local and global levels. • Implementers should be trained to understand AI limitations and risks and to communicate AI-assisted decisions responsibly. • For AI systems involving children, additional care is required for transparent, age-appropriate explanations and protecting their rights throughout the AI lifecycle. This framework helps organizations design and deploy AI that stakeholders can trust and engage with meaningfully. #AIExplainability #ResponsibleAI #HealthcareInnovation Peter Slattery, PhD The Alan Turing Institute

What’s the best way to document what AI decided—and why? Most people think AI documentation is about logging data — capturing outputs, timestamps, and probabilities. But I think that’s missing the real point. When humans make decisions, we can explain our intent. When AI makes a decision, it can’t. Because AI doesn’t have reasons — it has optimizations. And that, to me, changes everything. We don’t just need to record what the AI did. We need to explain what we taught it to optimize for. Right now, most documentation serves auditors and regulators. But the real value lies elsewhere — in understanding the alignment gap between human intent and machine logic. That gap is where trust, accountability, and learning live. Here’s how I think we can fix it: ✅ Document the goal — what was the AI trying to achieve? ✅ Note the key factors — what influenced the outcome most? ✅ Capture human intent — what assumptions shaped the model? ✅ Acknowledge uncertainty — what could still be wrong? This way, documentation becomes more than proof — it becomes memory. A shared record of how humans and machines reason together. So, what do you think — should AI documentation serve compliance, or should it serve understanding and accountability first? #AITransparency #AITrust #ResponsibleAI #AIEthics #HumanCenteredAI #AIGovernance

Our paper on transparency reports for large language models has been accepted to AI Ethics and Society! We’ve also released transparency reports for 14 models. If you’ll be in San Jose on October 21, come see our talk on this work. These transparency reports can help with: 🗂️ data provenance ⚖️ auditing & accountability 🌱 measuring environmental impact 🛑 evaluations of risk and harm 🌍 understanding how models are used   Mandatory transparency reporting is among the most common AI policy proposals, but there are few guidelines available describing how companies should actually do it. In February, we released our paper, “Foundation Model Transparency Reports,” where we proposed a framework for transparency reporting based on existing transparency reporting practices in pharmaceuticals, finance, and social media. We drew on the 100 transparency indicators from the Foundation Model Transparency Index to make each line item in the report concrete. At the time, no company had released a transparency report for their top AI model, so in providing an example we had to build a chimera transparency report with best practices drawn from 10 different companies.   In May, we published v1.1 of the Foundation Model Transparency Index, which includes transparency reports for 14 models, including OpenAI’s GPT-4, Anthropic’s Claude 3, Google’s Gemini 1.0 Ultra, and Meta’s Llama 2. The transparency reports are available as spreadsheets on our GitHub and in an interactive format on our website. We worked with companies to encourage them to disclose additional information about their most powerful AI models and were fairly successful – companies shared more than 200 new pieces of information, including potentially sensitive information about data, compute, and deployments. 🔗 Links to these resources in comment below!   Thanks to my coauthors Rishi Bommasani, Shayne Longpre, Betty Xiong, Sayash Kapoor, Nestor Maslej, Arvind Narayanan, Percy Liang at Stanford Institute for Human-Centered Artificial Intelligence (HAI), MIT Media Lab, and Princeton Center for Information Technology Policy

Your AI can be 100% compliant and still be unsafe. This has happened more than a few times in recent months, and it’s worth surfacing: AI launch meetings treating compliance as the finish line… when it should be the starting point. On paper, the project looked perfect. 🔸 Documentation? Complete. 🔸 Legal sign-offs? Secured. 🔸 Regulatory boxes? All ticked! But here’s the problem, the compliance review never asked: 🔸 How were training datasets sourced and validated? 🔸 Could patients understand how the AI reached its conclusions? 🔸 Who’s accountable when the AI gets it wrong? Here's the thing, Compliance checks boxes, Responsible AI earns trust. 🔹 Compliance is like passing a driving test 🔹 Responsibility is how you drive when no one’s watching 🔹 Compliance protects you from penalties 🔹 Responsibility protects people. With AI tools moving from pilot to frontline faster than policies can catch up, the gap between compliant and responsible is where harm happens. A compliant AI might flag a patient as low-risk, but without transparency, the clinician can’t see it missed a crucial symptom. One missed symptom → delayed care → worse outcomes → mistrust that can last years. Responsible AI starts with three pillars: 🔹 Ethical frameworks: Ground decisions in fairness, accountability, and beneficence, not just legal allowances. 🔹 Transparency: Let clinicians, patients, and regulators see how the AI works, its limits, and its data sources. 🔹 Oversight: Ensure a human is always answerable for AI actions, with mechanisms to detect and correct harm quickly. The real test of AI in healthcare isn’t whether it passes an audit, it’s whether it can earn and sustain trust. If you’re leading AI in healthcare today, this is the question your patients would want you to answer - which are you building? 💡This post is part of 'Rethinking Digital Health Innovation' (RDHI), empowering professionals to transform digital health beyond IT and AI myths. 💡The ongoing series and additional resources are available at www•enabler•xyz 💡Repost if this message resonates with you!

✨New working paper on the trade-offs involved in AI transparency in news 🤖📝 How does a global news organisation disclose its use of AI? Where, when and how should readers be told when algorithms shape the news they consume? Based on a case study of the Financial Times and led by Liz Lohn we argue that transparency about AI in news is best understood as a spectrum, evolving with tech advancements, commercial, professional and ethical considerations and shifting audience attitudes. 🔗Pre-print: https://lnkd.in/gV3dPXgS 1️⃣ AI‑transparency ≠ a binary. At the FT it’s a hybrid of policy, process and practice. Senior leadership sets explicit principles, cross‑functional panels vet new applications, and AI use is signposted in internal/external tools and reinforced through training. 2️⃣ Disclosure is calibrated to context. Internally, full disclosure aims to reduce frictions and surfaces errors early; externally, labels are scaled with autonomy and oversight. No‑human‑in‑the‑loop features (e.g. Ask FT) get prominent warnings, whereas AI‑assisted, journalist‑edited outputs (e.g. bullet‑point summaries) get lighter labelling. 3️⃣ Nine factors shape what, when & how the FT discloses AI use. These include legal/provider requirements, industry benchmarking, the degree of human oversight, the nature of the task, system novelty, audience expectations & research, perceived risk, commercial sensitivities and design constraints. 4️⃣ Persistent challenges include achieving consistent labelling (especially on mobile), breaking organisational silos, keeping pace with evolving models and norms, guarding against creeping human over‑reliance, and mitigating against “transparency backfire” where disclosures reduce trust. For those of you more academically interested in this, we argue that AI transparency at the FT is shaped by isomorphic pressures – regulations, peer practices and audience expectations – and by intersecting institutional logics. Internally, managerial and commercial logics push for efficient adoption and risk management; externally, professional journalism ethics and commercial imperatives drive an aim to remain trustworthy. Crucially, we argue that AI transparency is best seen as a spectrum: optimising one factor (e.g. maximum disclosure) can undermine others (e.g. perceived trust or revenue). There does not seem to be a one‑size‑fits‑all rule; instead transparency must adapt to org context, audiences and technology. We are very grateful to the team at the Financial Times, particularly Matthew Garrahan, for supporting this study from the outset – and to the participants from the FT who volunteered their precious time to help us in understanding this issue. Feedback welcome, especially on the theoretical section and the discussion as well as literature that we will have missed! So feel free to plug your own or other people’s material, all of which will be appreciated as Liz and I work towards a journal submission.

Explainable AI strengthens accountability and integrity in automation by making algorithmic reasoning transparent, ensuring fair governance, detecting bias, supporting compliance, and nurturing trust that sustains responsible innovation. Organizations that aim to integrate AI responsibly face a common challenge: understanding how decisions are made by their systems. Without clarity, compliance becomes fragile and ethics remain theoretical. Explainable AI brings visibility into this process, translating complex model logic into a language that regulators, auditors, and executives can actually understand. Transparency is not a luxury. It is a structural requirement for building trust in automated decision-making. When models are explainable, teams can trace outcomes, identify hidden biases, and take timely corrective action before risk escalates. This level of insight also helps align technology with existing regulatory frameworks, from GDPR principles to sector-specific governance standards. Embedding explainability within AI governance frameworks creates a bridge between innovation and responsibility. It helps organizations evolve without compromising accountability, ensuring that progress remains both human-centered and sustainable. #ExplainableAI #EthicalAI #AIGovernance #Compliance #Trust

Kevin Klyman: "📣📣 We just published the third annual Foundation Model Transparency Index! Our comprehensive study shows that AI companies have become less transparent in 2025. Some highlights from the paper: ➡️ Transparency on the decline: The average transparency score for AI companies declined from 58/100 in 2024 to 40/100 in 2025. xAI scores lower than any company we have ever assessed, releasing almost no information about its practices or its flagship model. ➡️ Companies withhold key information: Top tech companies release little or no information about the environmental impact of AI, whose data they use to build their systems, or whether the risk mitigations they put in place actually work. We definitively show that this information is not publicly available and that companies refuse to release it. ➡️ Companies share the capabilities of their models, but do not adequately evaluate risks. Just 4 of 13 companies comprehensively evaluated risks prior to release of their foundation model and report results upon release, and only IBM releases an externally reproducible risk evaluation. ➡️ Companies have changed their practices to release less information. In 2024, Meta and Mistral released technical reports alongside their flagship models (Llama 2 and Mistral 7B), but in 2025 neither released technical reports (for Llama 4 and Mistral Medium 3 respectively). As a result, Meta no longer discloses which risk mitigations it uses, quantitative evaluations of those risk mitigations, the amount and type of hardware it used to train its model, or prohibited model behaviors. ➡️ Our method: We break down transparency of AI companies into 100 indicators, develop concrete definitions and rubrics for those indicators, and send each company a transparency report template to fill out. This year 7 companies filled out the transparency report, and we independently assessed 6 other companies. We then worked with these companies to help them improve their disclosures, often resulting in companies disclosing new information to the public. You can read the full paper in the comments below! Thanks to the team behind the index - Alex Wan, Sayash Kapoor, Nestor Maslej, Shayne Longpre, Betty Xiong, Percy Liang, Rishi Bommasani! I'd also like to thank Stanford Institute for Human-Centered Artificial Intelligence (HAI) for supporting this work, Loredana Fattorini for making the visuals, and the Foundation Model Transparency Index board for their guidance Dr. Rumman Chowdhury, Daniel Ho, Arvind Narayanan, Danielle Allen and Daron Acemoglu. "

The next frontier in #AI isn't building models, it's building #trust. What good is a brilliant AI if no one in the organization trusts its recommendations? Explainable AI (XAI) is moving from a technical nicety to a commercial and operational necessity. A model's accuracy is irrelevant if a warehouse manager, or a supervisor cannot understand why it made a call. Gartner predicts that by 2026, over 50% of large enterprises will use XAI techniques to drive transparency. Trust is the currency of adoption. 1️⃣ Demanding #Interpretability from Vendors. Procurement criteria must include explainability. If you can't audit it, don't buy it. This is non-negotiable for high-stakes operations. 2️⃣ Implementing #Human-in-the-Loop Protocols. For critical decisions, designing workflows where AI recommends, but a human with context approves. This builds confidence and provides vital training data. 3️⃣ Communicating in #BusinessTerms, Not Math. Explanations must be causal and relevant. 4️⃣ Embeding #Ethics into the Model Lifecycle. Establishing clear ethical guidelines for AI use. Conducting regular bias audits. Transparency about limitations is a strength. The most powerful AI is the one people understand enough to trust and use fearlessly. #EthicalAI #ExplainableAI

Really interesting to see this level of transparency in a clinical AI tool. One of the biggest barriers to adoption has been the “black box” problem—clinicians are expected to trust outputs without understanding how they’re generated or where the evidence is coming from. That’s a tough ask in a field where accountability matters. What stands out here is the effort to make the reasoning process visible: how sources are selected, how uncertainty is handled, and when the system appropriately defers. That kind of traceability is exactly what many recent frameworks have been calling for to build clinician trust and enable safe integration into practice. I also appreciate that it doesn’t oversell the technology. Being explicit about limitations, edge cases, and failure modes is just as important as showcasing strengths—arguably more so. Transparency isn’t just a design choice; it’s foundational to whether these tools will actually be used at the bedside. Curious to see how this approach evolves, especially as more clinical AI tools move from demos into real-world workflows. https://lnkd.in/eetfjvWq

Medical AI can't earn clinicians' trust if we can't see how it works - this review shows where transparency is breaking down and how to fix it. 1️⃣ Most medical AI systems are "black boxes", trained on private datasets with little visibility into how they work or why they fail. 2️⃣ Transparency spans three stages: data (how it's collected, labeled, and shared), model (how predictions are made), and deployment (how performance is monitored). 3️⃣ Data transparency is hampered by missing demographic details, labeling inconsistencies, and lack of access - limiting reproducibility and fairness. 4️⃣ Explainable AI (XAI) tools like SHAP, LIME, and Grad-CAM can show which features models rely on, but still demand technical skill and may not match clinical reasoning. 5️⃣ Concept-based methods (like TCAV or ProtoPNet) aim to explain predictions in terms clinicians understand - e.g., redness or asymmetry in skin lesions. 6️⃣ Counterfactual tools flip model decisions to show what would need to change, revealing hidden biases like reliance on background skin texture. 7️⃣ Continuous performance monitoring post-deployment is rare but essential - only 2% of FDA-cleared tools showed evidence of it. 8️⃣ Regulatory frameworks (e.g., FDA's Total Product Lifecycle, GMLP) now demand explainability, user-centered design, and ongoing updates. 9️⃣ LLMs (like ChatGPT) add transparency challenges; techniques like retrieval-augmented generation help, but explanations may still lack faithfulness. 🔟 Integrating explainability into EHRs, minimizing cognitive load, and training clinicians on AI's limits are key to real-world adoption. ✍🏻 Chanwoo Kim, Soham U. Gadgil, Su-In Lee. Transparency of medical artificial intelligence systems. Nature Reviews Bioengineering. 2025. DOI: 10.1038/s44222-025-00363-w (behind paywall)