Papers with self-monitor
Think Twice, Generate Once: Safeguarding by Progressive Self-Reflection (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models generate coherent and contextually relevant text, but their deployment raises significant concerns about the potential for harmful or inappropriate content. |
| Approach: | They propose a novel inference-time technique that empowers LLMs to self-monitor and correct their outputs dynamically. |
| Outcome: | The proposed method reduces the attack success rate from 77.47% to 5.86%, to Llama-3.1-8B base from 89.70% to 5.56%, and to Qwen2.5-7B-Instruct from 44.44% to 3.84%, without additional training. |
Adaptive Platt Scaling with Causal Interpretations for Self-Reflective Language Model Uncertainty Estimates (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a new study examines the ability of large language models to self-monitor and ask for human intervention. |
| Approach: | They propose a formal analysis of LLM self-reflection for uncertainty estimation using domain adaptation theory. |
| Outcome: | The proposed method improves accuracy and human interpretation on reasoning tasks. |