TRACE: Single-Pass Decoding-Trace Risk Localization for Generation Calibration

arXiv:2609.35387 · cs.CL · Submitted 2026-09-28 · Read on arXiv

cs.CL

Submitted: 2026-09-28

Updated: 2026-09-28

Comments: EMNLP 2026 Findings

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Trace — 280× in this paper · explained in 2 episodes
• Calibration — 59× in this paper · explained in 7 episodes
• Aggregation — 14× in this paper · explained in 1 episode
• Robustness — 13× in this paper · explained in 5 episodes
• Verifier — 7× in this paper · explained in 2 episodes
• Ablation — 6× in this paper · explained in 1 episode
• Hallucination — 4× in this paper · explained in 3 episodes
• Consistency — 3× in this paper · explained in 3 episodes
• Generalization — 3× in this paper · explained in 13 episodes
• Accuracy — 2× in this paper · explained in 1 episode
• LLM-as-a-Judge — 2× in this paper · explained in 3 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Distribution Shift — 1× in this paper · explained in 5 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Generalizability — 1× in this paper · explained in 6 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Self-consistency — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Uncertainty Quantification — 1× in this paper · explained in 8 episodes

Sources

• Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
• How Confident Is the First Token? An Uncertainty-Calibrated Prompt Optimization Framework for Large Language Model Classification and Understanding
• The Llama 3 Herd of Models
• Mistral 7B
• Language Models (Mostly) Know What They Know
• HALT: Hallucination Assessment via Log-probs as Time series
• Gemma 2: Improving Open Language Models at a Practical Size
• Qwen3 Technical Report
• Qwen2 Technical Report
• Qwen2.5 Technical Report
• Useful Confidence Measures: Beyond the Max Score
• EDIS: Diagnosing LLM Reasoning via Entropy Dynamics

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering