Arize AI debuted new capabilities for fine tuning and monitoring large language models (LLMs). The offering brings greater control and insight to teams looking to build with LLMs.
Now available as part of the free product, Arize's LLM observability tool evaluates LLM responses, pinpoints where to improve with prompt engineering, and identifies fine-tuning opportunities using vector similarity search.
The new offering is built to work in tandem with Phoenix, an open source library for LLM evaluation.
Leveraging Arize, teams can:
- Detect Problematic Prompts and Responses: By monitoring a model's prompt/response embeddings performance using LLM evaluation scores and cluster analysis, teams can narrow in on areas their LLM needs improvement.
- Analyze Clusters Using LLM Evaluation Metrics and GPT-4: Automatically generate clusters of semantically similar data points and sort by performance. Arize supports LLM-assisted evaluation metrics, task-specific metrics, along with user feedback. An integration with ChatGPT also enables teams to analyze clusters for deeper insights.
- Improve LLM Responses with Prompt Engineering: Pinpoint prompt/response clusters with low evaluation scores. Workflows suggest ways to augment prompts to help your LLM models generate better responses and improve acceptance rates.
- Fine-Tune Your LLM Using Vector Similarity Search: Find problematic clusters, such as inaccurate or unhelpful responses, to fine-tune with better data. Vector-similarity search clues you into other examples of issues emerging, so you can begin data augmentation before they become systemic.
- Leverage Pre-Built Clusters for Prescriptive Analysis: Use pre-built global clusters identified by Arize algorithms, or define custom clusters of your own to simplify RCA and make prescriptive improvements to your generative models.
"Despite the power of these models, the risk of deploying LLMs in high risk environments can be immense," notes Jason Lopatecki, CEO and Co-Founder of Arize. "As new applications get built, Arize LLM observability is here to provide the right guardrails to innovate with this new technology safely."
The Latest
An overwhelming majority of IT leaders (95%) believe the upcoming wave of AI-powered digital transformation is set to be the most impactful and intensive seen thus far, according to The Science of Productivity: AI, Adoption, And Employee Experience, a new report from Nexthink ...
Overall outage frequency and the general level of reported severity continue to decline, according to the Outage Analysis 2025 from Uptime Institute. However, cyber security incidents are on the rise and often have severe, lasting impacts ...
In March, New Relic published the State of Observability for Media and Entertainment Report to share insights, data, and analysis into the adoption and business value of observability across the media and entertainment industry. Here are six key takeaways from the report ...
Regardless of their scale, business decisions often take time, effort, and a lot of back-and-forth discussion to reach any sort of actionable conclusion ... Any means of streamlining this process and getting from complex problems to optimal solutions more efficiently and reliably is key. How can organizations optimize their decision-making to save time and reduce excess effort from those involved? ...
As enterprises accelerate their cloud adoption strategies, CIOs are routinely exceeding their cloud budgets — a concern that's about to face additional pressure from an unexpected direction: uncertainty over semiconductor tariffs. The CIO Cloud Trends Survey & Report from Azul reveals the extent continued cloud investment despite cost overruns, and how organizations are attempting to bring spending under control ...
According to Auvik's 2025 IT Trends Report, 60% of IT professionals feel at least moderately burned out on the job, with 43% stating that their workload is contributing to work stress. At the same time, many IT professionals are naming AI and machine learning as key areas they'd most like to upskill ...
Businesses that face downtime or outages risk financial and reputational damage, as well as reducing partner, shareholder, and customer trust. One of the major challenges that enterprises face is implementing a robust business continuity plan. What's the solution? The answer may lie in disaster recovery tactics such as truly immutable storage and regular disaster recovery testing ...
IT spending is expected to jump nearly 10% in 2025, and organizations are now facing pressure to manage costs without slowing down critical functions like observability. To meet the challenge, leaders are turning to smarter, more cost effective business strategies. Enter stage right: OpenTelemetry, the missing piece of the puzzle that is no longer just an option but rather a strategic advantage ...
Amidst the threat of cyberhacks and data breaches, companies install several security measures to keep their business safely afloat. These measures aim to protect businesses, employees, and crucial data. Yet, employees perceive them as burdensome. Frustrated with complex logins, slow access, and constant security checks, workers decide to completely bypass all security set-ups ...
In MEAN TIME TO INSIGHT Episode 13, Shamus McGillicuddy, VP of Research, Network Infrastructure and Operations, at EMA discusses hybrid multi-cloud networking strategy ...