15 accepted papers
We present Auto-BenchmarkCard, a workflow for generating validated descriptions of AI benchmarks. Benchmark documentation is often incomplete or inconsistent, making it difficult to interpret and compare benchmarks across tasks or domains. Auto-BenchmarkCard addresses this gap by combining multi-age
We present Risk Atlas Nexus, an open source system for governing AI risks. The system unifies several risk classification frameworks through a common ontology. Given an AI application use case (called an intent), the system estimates risks and associated mitigations that are linked to identified ris
Large language models (LLMs) are powerful tools capable of handling diverse tasks. Comparing and selecting appropriate LLMs for specific tasks requires systematic evaluation methods, as models exhibit varying capabilities across different domains. However, finding suitable benchmarks is difficult gi…
We present EvalAssist, a framework that simplifies the LLM- as-a-judge workflow. The system provides an online criteria development environment, where users can interactively build, test, and share custom evaluation criteria in a structured and portable format. A library of LLM based evaluators is m…
Building pluralistic AI requires designing models that are able to be shaped to represent a wide range of value systems and cultures. Achieving this requires first being able to evaluate the degree to which a given model is capable of reflecting various personas. To this end, we propose a benchmark…
Large language models (LLMs) have achieved remarkable success in generative tasks, yet they often fall short in ensuring the factual accuracy of their outputs thus limiting their reliability in real-world applications where correctness is critical. In this paper, we present FactReasoner, a novel neu
The deployment of language models in real-world applications exposes users to various risks, including hallucinations and harmful or unethical content. These challenges highlight the urgent need for robust safeguards to ensure safe and responsible AI. To address this, we introduce Granite Guardian,…
Bringing a new AI system into a production environment involves multiple different stakeholders such as business owners, risk officer, ethics officers approving the AI System for a specific usage. Governance frameworks typically include multiple manual steps, including curating information needed to…
Bias mitigation algorithms differ in their definition of bias and how they go about achieving that objective. Bias mitigation algorithms impact different cohorts differently and allowing end users and data scientists to understand the impact of these differences in order to make informed choices is…
Modern language models, while sophisticated, exhibit some inherent shortcomings, particularly in conversational settings. We claim that many of the observed shortcomings can be attributed to violation of one or more conversational principles. By drawing upon extensive research from both the social s…
Retrieval-augmented generation (RAG) has emerged as a promising solution to mitigate the limitations of large language models (LLMs), such as hallucinations and outdated information. However, it remains unclear how LLMs handle knowledge conflicts arising from different augmented retrieved passages,…
Cookies are designed to enable more accurate identification and tracking of user behavior, in turn allowing for more personalized ads and better performing ad campaigns. Given the additional information that is recorded, questions related to privacy and fairness naturally arise. How does a user's co…
Understanding the differences between machine learning (ML) models is of interest in scenarios ranging from choosing amongst a set of competing models, to updating a deployed model with new training data. In these cases, we wish to go beyond differences in overall metrics such as accuracy to identif…
Interpretable and explainable machine learning has seen a recent surge of interest. We focus on safety as a key motivation behind the surge and make the relationship between interpretability and safety more quantitative. Toward assessing safety, we introduce the concept of *maximum deviation* via an…
AI solutions are heavily dependant on the quality and accuracy of the input training data, however the training data may not always fully reflect the most up-to-date policy landscape or may be missing business logic. The advances in explainability have opened the possibility of allowing users to int…