LLM-friendly knowledge framework boosts customer support automation

Researchers presented a new framework at COLING 2025 that restructures enterprise workflows into large language model friendly formats to improve automated customer support performance and scalability.

Researchers affiliated with a leading Silicon Valley technology company have introduced a new framework for making enterprise workflows more readable and actionable for large language models in customer support environments. Presented at the 31st International Conference on Computational Linguistics (COLING 2025) in a study titled “LLM-Friendly Knowledge Representation for Customer Support,” the work focuses on restructuring complex operational processes so that automated support systems can interpret them more effectively. The framework is designed to improve scalability, interpretability, and decision quality across intricate operational settings by translating business logic into machine-optimized formats.

The central innovation in the study is the Intent, Context, and Action format, a pseudocode-style representation that recasts operational workflows into a structure optimized for large language model comprehension. Experiments reported in the paper show that ICA improves model interpretability and enables more accurate action predictions, achieving up to a 25 percent accuracy gain and a 13 percent reduction in manual processing time. The authors report that the ICA methodology establishes a new benchmark for customer support applications and can be extended to other knowledge-intensive sectors such as legal and finance. The study concludes that by reformulating operational knowledge into ICA, organizations can embed structured reasoning in automated systems while maintaining clearer transparency over how decisions are made.

To address the shortage of suitable training data, the researchers also propose a synthetic data generation pipeline that minimizes the need for manual labeling. The method constructs training instances by simulating user queries, contextual conditions, and decision-tree structures so that models can learn reasoning patterns that reflect real-world support workflows. According to the experiments, this approach reduces training costs and allows smaller open-source models to approach the performance and latency of larger systems, which the authors describe as a meaningful step toward scalable enterprise artificial intelligence development. Among the contributors is Hanchen Su, a staff machine learning engineer with experience in machine learning, natural language processing, and statistical learning, whose background spans intelligent customer service, pricing strategy, recommendation systems, and large-scale data processing across multiple technology companies and entrepreneurial projects.

55

Impact Score

Best content artificial intelligence tools for modern digital strategy

Content-focused artificial intelligence platforms are transforming how marketers plan, create, and optimize text, visuals, and audio, shifting teams from production bottlenecks to scalable, data-driven workflows. Success now depends on choosing the right tools, integrating them into existing systems, and pairing automation with strong human oversight and ethics.

Designing a healthier artificial intelligence future in us healthcare

The article outlines how consumer expectations and organizational readiness must align for artificial intelligence to deliver meaningful, ethical value across the patient journey in the U.S. healthcare system. It highlights three core opportunity areas and the internal capabilities required to scale them responsibly.

Intel targets pro visualization with Arc Pro B70 and B65 battlemage gpus

Intel is preparing Arc Pro B70 and B65 battlemage desktop gpus built around the BMG-G31 die, aimed at professional visualization, workstation, and local Artificial Intelligence workloads rather than gaming. The move underscores a strategic focus on high memory capacity and price performance in the pro segment while larger gaming cards remain delayed.

Contact Us

Got questions? Use the form to contact us.

Contact Form

Clicking next sends a verification code to your email. After verifying, you can enter your message.