LLMs currently face significant challenges when it comes to truthfulness. Understanding these limitations is essential for any business considering leveraging LLMs.

We explore the current state of responsible AI, examining the lack of standardized evaluations for LLMs, the discovery of complex vulnerabilities in these models, the growing concern among businesses about AI risks, and the challenges posed by LLMs outputting copyrighted material.

A new study from Harvard University reveals how LLMs can be manipulated to boost a product's visibility and ranking in recommendations.

InterpretML is a valuable tool for unlocking the power of interpretable AI in traditional machine learning models. While it may have limitations when it comes to directly interpreting LLMs, the principles of interpretability and transparency remain crucial in the age of generative AI.

A recent critique calls into question a prominent AI transparency benchmark, illustrating the challenges in evaluating something as complex as transparency.

A recent critique calls into question a prominent AI transparency benchmark, illustrating the challenges in evaluating something as complex as transparency.

AI experts Alexandra Luccioni and Anna Rogers take a critical look at LLMs, analyzing common claims and assumptions while identifying issues and proposing ways forward.

In 2019, a research paper proposed "model cards" as a way to increase transparency into AI systems and mitigate their potential harms.

A thought-provoking paper from computer scientists raises important concerns about the AI community's pursuit of ever-larger language models.

A research paper proposes formal internal audits as a mechanism for technology companies to ensure their artificial intelligence (AI) aligns with ethical priorities before deployment.

A study from AI researchers at OpenAI demonstrates how large language models like chatbots can be adapted to reflect specific societal values through a simple "fine-tuning" process.

A new study provides insights into the complex processes and people behind ML data work.

In a recent paper, researchers Mehtab Khan and Alex Hanna highlight the need for greater scrutiny, transparency, and accountability in how massive datasets for machine learning models are created.

Machine learning models rely heavily on their training datasets, inheriting inherent biases and limitations. This research proposes "datasheets for datasets" increasing transparency and mitigating risks.

Backpack models have an internal structure that is more interpretable and controllable compared to existing models like BERT and GPT-3.

Recent advances in AI language models like GPT-4 and Claude 2 have enabled impressively fluent text generation. However, new research reveals these models may perpetuate harmful stereotypes and assumptions through the narratives they construct.

Emily Bender, Alex Hanna, and Hannah Zeavin discuss misguided uses of AI in the mental health area.

Researchers at Anthropic recently published a paper demonstrating a constitutional AI technique. Their goal was to make the assistants helpful, while avoiding harmful, dangerous, or unethical content.

In a paper titled "What the DAAM: Interpreting Stable Diffusion Using Cross Attention", researchers propose a method called DAAM (Diffusion Attentive Attribution Maps) to analyze how words in a prompt influence different parts of the generated image.