Surprisal minimization over goal-directed alternatives generated by language models provides the strongest account of production choices in open-ended dialogue compared to uniform information density or length-based costs.
Title resolution pending
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
years
2026 6verdicts
UNVERDICTED 6representative citing papers
FLASH Policy uses sparse Legendre polynomial trajectory fitting and history-anchored flow matching to enable single-step inference for visuomotor control, reporting 31.4 ms per-episode latency and >=92% success on five simulated plus two real manipulation tasks.
The paper formulates LLM-as-judge evaluation as a two-stage missing-data problem and derives sample-size formulas via doubly robust estimators to achieve desired power while allocating more human reviews where LLM predictability is low.
Hesitator is a theory-grounded simulator that separates utility-based item selection from overload-aware commitment decisions to reduce unrealistic high acceptance rates in conversational recommender evaluations.
A framework uses stance detection, linear dimensionality reduction, and neural potential landscapes to recover a 3D stance space explaining 45% variance and to visualize large-scale shifts across platforms and years.
Tonic electrodermal activity responds additively to cognitive stress and physical exertion with no interaction, making it the strongest candidate for stress detection during activity among the five signals tested.
citing papers explorer
-
Surprisal Minimisation over Goal-directed Alternatives Predicts Production Choice in Dialogue
Surprisal minimization over goal-directed alternatives generated by language models provides the strongest account of production choices in open-ended dialogue compared to uniform information density or length-based costs.
-
FLASH: Efficient Visuomotor Policy via Sparse Sampling
FLASH Policy uses sparse Legendre polynomial trajectory fitting and history-anchored flow matching to enable single-step inference for visuomotor control, reporting 31.4 ms per-episode latency and >=92% success on five simulated plus two real manipulation tasks.
-
Augmenting Human Evaluation with LLM Judges: How Many Human Reviews Do You Need?
The paper formulates LLM-as-judge evaluation as a two-stage missing-data problem and derives sample-size formulas via doubly robust estimators to achieve desired power while allocating more human reviews where LLM predictability is low.
-
Decision-aware User Simulation Agent for Evaluating Conversational Recommender Systems
Hesitator is a theory-grounded simulator that separates utility-based item selection from overload-aware commitment decisions to reduce unrealistic high acceptance rates in conversational recommender evaluations.
-
Mapping the Winds of Stance Dynamics using Potential Landscape Models
A framework uses stance detection, linear dimensionality reduction, and neural potential landscapes to recover a 3D stance space explaining 45% variance and to visualize large-scale shifts across platforms and years.
-
Separating Acute Psychological Stress from Physical Exertion in Biometric Signals
Tonic electrodermal activity responds additively to cognitive stress and physical exertion with no interaction, making it the strongest candidate for stress detection during activity among the five signals tested.