A fixed learned sentence inserted into a frozen LLM's prompt steers its uncertainty so that lowest-entropy answer selection avoids misleading passages, raising mean F1 from 0.5148 to 0.5339 across five QA benchmarks.
How Well Does First-Token Entropy Approximate Word Entropy as a Psycholinguistic Predictor?
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Contextual entropy is a psycholinguistic measure capturing the anticipated difficulty of processing a word just before it is encountered. Recent studies have tested for entropy-related effects as a potential complement to well-known effects from surprisal. For convenience, entropy is typically estimated based on a language model's probability distribution over a word's first subword token. However, this approximation results in underestimation and potential distortion of true word entropy. To address this, we generate Monte Carlo (MC) estimates of word entropy that allow words to span a variable number of tokens. Regression experiments on reading times show divergent results between first-token and MC word entropy, suggesting a need for caution in using first-token approximations of contextual entropy.
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
LODESTAR: Trustworthy Entropy Is Navigated, Not Merely Measured -- Reinforced Polarizer Keeps a Frozen LLM from Being Confidently Misled by the Wrong Evidence
A fixed learned sentence inserted into a frozen LLM's prompt steers its uncertainty so that lowest-entropy answer selection avoids misleading passages, raising mean F1 from 0.5148 to 0.5339 across five QA benchmarks.