arXiv Computation and Language
Do small language models know what they don't know?
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
Hugging Face Trending Papers
3d ago
Probability is Not Enough: Exploring and Counting Divergent Tokens for Reasoning Uncertainty Quantification in LLMs
As the chain-of-thought reasoning capabilities of large language models improve, evaluating and calibrating their reasoning confidence is becoming increasingly important for quantifying the uncertaint...
arXiv AI
3d ago
Probability is Not Enough: Exploring and Counting Divergent Tokens for Reasoning Uncertainty Quantification in LLMs
The paper introduces Divergent Token Confidence (DTC), a method that estimates large language model confidence by counting tokens where two models strongly disagree during decoding. DTC uses Jensen-Shannon divergence between next-token distributions along the same reasoning trajectory and shows a near-negative correlation with answer accuracy. Experiments on multiple model families and six mathematical benchmarks demonstrate that DTC improves calibration over traditional probability-based and verbalized baselines, achieving lower expected calibration errors in both white-box and black-box settings.
arXiv AI
3d ago
Cross-Entropy Guided Routing in Mixture-of-Experts Large Language Models
The paper introduces two token-error supervision methods for sparse mixture-of-experts (MoE) large language models, aligning routing affinities with token-level cross-entropy loss. The first method predicts an error score per expert and uses it to adjust affinities before top‑K selection, while the second directly aligns router affinities to the model’s objective without extra heads or inference changes. Experiments on Granite and ARC‑Challenge show accuracy gains of about 2.3–2.94 percentage points over a parameter‑matched baseline, preserving the native sparse execution budget.
arXiv AI
Sep 3
From Tokens to Semantics: Leveraging Complementary Signals for Hallucination Detection in Black-Box LLMs
The paper investigates hallucination detection in black‑box large language models by leveraging two accessible signals: semantic entropy, which captures disagreement among sampled response meanings, and token‑level uncertainty derived from log‑probabilities. It introduces a TopK aggregation technique, a hybrid CoCoA method combining uncertainty with semantic dissimilarity, and two supervised approaches—Gated and Stacked—that integrate token and semantic features. Across seven benchmarks and four language models, the supervised Stacked method performs best in many cases, while TopK and CoCoA remain competitive without labeled data, though all methods require careful threshold calibration.
arXiv Computation and Language
Aug 28
The Score Granularity Gap in Black-Box LLM Classification: A Comparative Study of Confidence Constructions
The paper investigates the "score granularity gap" in black-box large language model (LLM) classifiers, asking how finely a confidence score can be thresholded for deployment. By comparing seven confidence construction methods across 25 model-dataset pairs, the authors find that single-shot verbalized confidence, when properly converted to a probability, ranks well but offers only a few distinct threshold values, limiting operational flexibility. The study also shows that multi-query aggregation can improve weak models but may harm strong ones, and provides concrete guidance for deployment trade-offs.
arXiv AI
Aug 5
LogitScope: A Framework for Analyzing LLM Uncertainty Through Information Metrics
arXiv:2603. 24929v2 Announce Type: replace Abstract: Understanding and quantifying uncertainty in large language model (LLM) outputs is critical for reliable deployment.