# Efficiently Deploying LLMs with Controlled Risk

arXiv: https://arxiv.org/abs/2410.02173 · HTML: https://mlsanity.com/paper/2410.02173/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 48 references that are in the map.
- First posted on arXiv 3 Oct 2024.

## Builds on (most cited first, 30 of 38)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs](https://mlsanity.com/paper/2306.13063/) (2023)
- [FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance](https://mlsanity.com/paper/2305.05176/) (2023)
- [Selective Classification for Deep Neural Networks](https://mlsanity.com/paper/1705.08500/) (2017)
- [Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation](https://mlsanity.com/paper/2302.09664/) (2023)
- [SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models](https://mlsanity.com/paper/2303.08896/) (2023)
- [Teaching Models to Express Their Uncertainty in Words](https://mlsanity.com/paper/2205.14334/) (2022)
- [The Internal State of an LLM Knows When It's Lying](https://mlsanity.com/paper/2304.13734/) (2023)
- [LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion](https://mlsanity.com/paper/2306.02561/) (2023)
- [How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answering](https://mlsanity.com/paper/2012.00955/) (2020)
- [Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing](https://mlsanity.com/paper/2404.14618/) (2024)
- [INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection](https://mlsanity.com/paper/2402.03744/) (2024)
- [Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models](https://mlsanity.com/paper/2305.19187/) (2023)
- [A Survey on Knowledge Distillation of Large Language Models](https://mlsanity.com/paper/2402.13116/) (2024)
- [Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs](https://mlsanity.com/paper/2406.15927/) (2024)
- [RouterBench: A Benchmark for Multi-LLM Routing System](https://mlsanity.com/paper/2403.12031/) (2024)
- [Out-of-Distribution Detection and Selective Generation for Conditional Language Models](https://mlsanity.com/paper/2209.15558/) (2022)
- [Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities](https://mlsanity.com/paper/2405.20003/) (2024)
- [Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Models](https://mlsanity.com/paper/2311.08692/) (2023)
- [Large Language Model Cascades with Mixture of Thoughts Representations for Cost-efficient Reasoning](https://mlsanity.com/paper/2310.03094/) (2023)
- [AutoMix: Automatically Mixing Language Models](https://mlsanity.com/paper/2310.12963/) (2023)
- [Language Model Cascades: Token-level uncertainty and beyond](https://mlsanity.com/paper/2404.10136/) (2024)
- [Fly-Swat or Cannon? Cost-Effective Language Model Choice via Meta-Modeling](https://mlsanity.com/paper/2308.06077/) (2023)

## Built on by (most cited first, 5 of 5)

- [Cascaded Language Models for Cost-effective Human-AI Decision-Making](https://mlsanity.com/paper/2506.11887/) (2025)
- [Rational Tuning of LLM Cascades via Probabilistic Modeling](https://mlsanity.com/paper/2501.09345/) (2025)
- [Economic Evaluation of LLMs](https://mlsanity.com/paper/2507.03834/) (2025)
- [Streaming Model Cascades for Semantic SQL](https://mlsanity.com/paper/2604.00660/) (2026)
- [Do Small Language Models Know When They're Wrong? Confidence-Based Cascade Scoring for Educational Assessment](https://mlsanity.com/paper/2604.19781/) (2026)

## Abstract (arXiv)

Deploying large language models in production requires simultaneous attention to efficiency and risk control. Prior work has shown the possibility to cut costs while maintaining similar accuracy, but has neglected to focus on risk control. By contrast, here we present hierarchical chains with multi-level abstention (HCMA), which use model-intrinsic uncertainty to delegate queries along the LLM intelligence hierarchy, enabling training-free model switching based solely on black-box API calls. Our framework presents novel trade-offs between efficiency and risk. For example, deploying HCMA on MMLU cuts the error rate of Llama3 405B by 30% when the model is allowed to abstain on 20% of the queries. To calibrate HCMA for optimal performance, our approach uses data-efficient logistic regressions (based on a simple nonlinear feature transformation), which require only 50 or 100 labeled examples to achieve excellent calibration error (ECE), cutting ECE by 50% compared to naive Platt scaling. On free-form generation tasks, we find that chain-of-thought is ineffectual for selective prediction, whereas zero-shot prompting drives error to 0% on TruthfulQA at high abstention rates. As LLMs are increasingly deployed across computing environments with different capabilities (such as mobile, laptop, and cloud), our framework paves the way towards maintaining deployment efficiency while putting in place sharp risk controls.