Papers by Ali Razghandi
CER: Confidence Enhanced Reasoning in LLMs (2025.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to enhance the reliability of Large Language Models (LLMs) in complex reasoning tasks are limited by their limitations. |
| Approach: | They propose an uncertainty-aware framework to enhance the reliability of Large Language Models . they quantify the confidence of intermediate answers and evaluate the reliability based on these confidences a way that reflects the reliability. |
| Outcome: | The proposed approach improves accuracy of large language models in math and open-domain tasks by 7.4% and 5.8% over baseline approaches. |