Challenge: Large Language Models (LLMs) have revolutionized inference across diverse natural language tasks, with larger models performing better but at higher computational costs.
Approach: They propose a confidence-driven strategy that dynamically selects the most suitable model based on confidence estimates.
Outcome: The proposed approach reduces token usage by approximately 60% and improves cost efficiency on the Massive Multitask Language Understanding (MMLU) benchmark.

Similar Papers

A Survey of Confidence Estimation and Calibration in Large Language Models (2024.naacl-long)

Copied to clipboard

Challenge: Large language models (LLMs) have demonstrated impressive capabilities across a wide range of tasks in various domains, but they can be unreliable due to factual errors in their generations.
Approach: They summarize recent advances in LLM confidence estimation and calibration and outline their main lessons learned.
Outcome: The proposed methods can be used to assess the reliability of models and to calibrate them across tasks.
All Roads Lead to Rome: Graph-Based Confidence Estimation for Large Language Model Reasoning (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for confidence estimation are primarily designed for factual QA tasks and fail to generalize to reasoning tasks.
Approach: They propose a set of training-free, graph-based confidence estimation methods tailored to reasoning tasks that exploit graph properties such as centrality, path convergence, and path weighting.
Outcome: The proposed methods improve confidence estimation and performance on two downstream tasks.
Uncertainty-Aware Answer Selection for Improved Reasoning in Multi-LLM Systems (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to selecting reliable responses from multiple LLMs often depend on external verifiers, human evaluators, or self-consistency techniques.
Approach: They propose a calibrated log-likelihood-based selection framework to improve multi-LLM performance.
Outcome: The proposed method outperforms majority voting and exceeds self-consistency performance when using a large number of model calls.
MlingConf: A Comprehensive Study of Multilingual Confidence Estimation on Large Language Models (2025.findings-acl)

Copied to clipboard

Challenge: Existing studies on LLM confidence estimations in languages other than English have been limited to English.
Approach: They propose to use question-related language to prompt LLMs to assess their confidence in large language models.
Outcome: The proposed model improves on question-related language prompts for LS tasks, while English exhibits notable linguistic dominance in confidence estimations.
Confidence Under the Hood: An Investigation into the Confidence-Probability Alignment in Large Language Models (2024.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) are increasingly used in high-stakes areas such as healthcare, law, and education.
Approach: They propose a concept of Confidence-Probability Alignment that connects an LLM’s internal confidence to the confidence conveyed in the model’s response when explicitly asked about its certainty.
Outcome: The proposed model shows the strongest confidence-probability alignment across a wide range of tasks.
Confidence-Calibrated Small-Large Language Model Collaboration for Cost-Efficient Reasoning (2026.eacl-long)

Copied to clipboard

Challenge: Large language models (LLMs) have superior reasoning capabilities compared to small language models, but incur substantially higher inference costs.
Approach: They propose a system that cascades an LLM with an SLM to achieve a balance between accuracy and cost in complex reasoning tasks.
Outcome: The proposed system improves the SLM’s reasoning ability and confidence calibration across diverse datasets and model backbones.
Evaluating Large Language Models for Confidence-based Check Set Selection (2025.findings-acl)

Copied to clipboard

Challenge: Large language models have shown promise in automating high-labor data tasks, but their tendency to answer despite uncertainty and their difficulty handling long input contexts robustly are key challenges for adoption.
Approach: They propose to use LLMs to prioritize information needing human judgment to identify low-confidence outputs for human review through "check set selection" using social media monitoring, they define the "check sets" as a list of tweets escalated to the disaster manager when the LLM has the least confidence.
Outcome: The proposed approach outperforms random-sample check set selection in disaster tweet classification.
SelectLLM: Query-Aware Efficient Selection Algorithm for Large Language Models (2025.findings-acl)

Copied to clipboard

Challenge: Existing large language models struggle with complex tasks such as factually-grounded reasoning and planning due to inherent training biases, model size constraints, and the quality or diversity of pre-training datasets.
Approach: They propose a novel algorithm to select the most suitable LLMs from a large pool and use it to efficiently generalize and perform tasks.
Outcome: The proposed model outperforms existing ensemble-based baselines and achieves competitive performance with similarly sized top-performing LLMs while maintaining efficiency.
AdaptEvolve: Improving Efficiency of Evolutionary AI Agents through Adaptive Model Selection (2026.findings-acl)

Copied to clipboard

Challenge: Existing routing strategies rely on static heuristics or external controllers to optimize performance.
Approach: They propose a framework that leverages intrinsic generation confidence to estimate solvability.
Outcome: Empirical results show that confidence-driven selection yields favorable Pareto frontier . computational cost of state-of-the-art large language models remains a key barrier to scalable deployment .
Can Unconfident LLM Annotations Be Used for Confident Conclusions? (2025.naacl-long)

Copied to clipboard

Challenge: Large language models (LLMs) have shown high agreement with human raters across a variety of tasks, demonstrating potential to ease the challenges of human data collection.
Approach: They propose a method that combines LLM annotations and LLM confidence indicators to strategically select which human annotations to use.
Outcome: The proposed method produces accurate estimates and valid confidence intervals while reducing the number of human annotations by over 25%.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations