AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

Interpreting Fedspeak with Confidence: A LLM-Based Uncertainty-Aware Framework Guided by Monetary Policy Transmission Paths

Rui Yao, Qi Chai, Jinhai Yao, Siyuan Li, Junhao Chen, Qi Zhang, Hao Wang

AAAI 2026 · Large language models › Language, safety and interpretability · approach: Uncertainty quantification for LLMs · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add dynamic uncertainty decoding (PU) (ablation)fine-tuned Qwen3-14B with augmentation · FOMC (all categories)Weighted F1: 0.7378 -> 0.7426Improved
add monetary policy transmission path information (ablation)Qwen3-14B framework · FOMC (all categories)Weighted F1: 0.6699 -> 0.7426Improved
add financial entity relationships (ablation)Qwen3-14B framework · FOMC (all categories)Weighted F1: 0.6551 -> 0.7426Improved
add all proposed modules to fine-tuned Qwen3 (ablation)Qwen3-14B · FOMC (all categories)Macro F1: 0.6360 -> 0.7327Improved
add rules to the augmentation prompt (ablation)Gemini-2.5-Pro augmentation prompt · FOMC (augmentation prompt, Gemini-2.5-Pro)Weighted F1: 0.5073 -> 0.6695Improved
add examples to the augmentation prompt (ablation)Gemini-2.5-Pro augmentation prompt · FOMC (augmentation prompt, Gemini-2.5-Pro)Weighted F1: 0.5024 -> 0.6695Improved
use text-based stance labels instead of numeric labels (ablation)fine-tuned Qwen3-14B · FOMC (all categories)Weighted F1: 0.7114 -> 0.7378Improved
fine-tune with LoRA on FOMC dataGLM-4-9B · FOMC (all categories)Macro F1: 0.3152 -> 0.6390Improved
cluster label tokens before uncertainty computation (ablation)uncertainty decoding · FOMC (all categories)Weighted F1: 0.7404 -> 0.7426Improved
apply framework to Phi-4 instead of Qwen-3Phi-4 · FOMC (transfer to Phi-4)Weighted F1: 0.7225 -> 0.7241No clear effect
use conservative/greedy-k variants instead of greedy-c with candidate sampling (ablation)uncertainty decoding · FOMC (all categories)Weighted F1: 0.7426 -> 0.7364Hurt
use Ours instead of GPT-4.1press conference transcripts · FOMC (press conference)Weighted F1: 0.6900 -> 0.6699Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy