Skip to content
<title>Channels - Surprisal Minimisation over Goal-directed Alternatives Predicts Production Choice in Dialogue :: FRELIP Discovery
-
On the Proper Treatment of Units in Surprisal Theory
-
The Frequency Confound in Language-Model Surprisal and Metaphor Novelty
-
Reasoning over Object Descriptions Improves Coreference Resolution in Task-Based Dialogue Systems
-
DGPO: Beyond Pairwise Preferences with Directional Consistent Groupwise Optimization
-
Shadow-Loom: Causal Reasoning over Graphical World Model of Narratives
-
Directed Social Regard: Surfacing Targeted Advocacy, Opposition, Aid, Harms, and Victimization in Online Media
-
Repetition over Diversity: High-Signal Data Filtering for Sample-Efficient German Language Modeling
-
Beyond Confidence: Rethinking Self-Assessments for Performance Prediction in LLMs
-
Beyond Semantics: An Evidential Reasoning-Aware Multi-View Learning Framework for Trustworthy Mental Health Prediction
-
Multi-Level Narrative Evaluation Outperforms Lexical Features for Mental Health
-
Geometry-Calibrated Conformal Abstention for Language Models
-
From Unstructured Recall to Schema-Grounded Memory: Reliable AI Memory via Iterative, Schema-Aware Extraction
-
MM-StanceDet: Retrieval-Augmented Multi-modal Multi-agent Stance Detection
-
DPN-LE: Dual Personality Neuron Localization and Editing for Large Language Models
-
Can AI Be a Good Peer Reviewer? A Survey of Peer Review Process, Evaluation, and the Future
-
Beyond Semantics: Measuring Fine-Grained Emotion Preservation in Small Language Model-Based Machine Translation
-
Ease of dependency distance minimization in star-like structures
-
Models Recall What They Violate: Constraint Adherence in Multi-Turn LLM Ideation
-
Universal statistical laws governing culinary design
-
Latent-GRPO: Group Relative Policy Optimization for Latent Reasoning
-
Stable Behavior, Limited Variation: Persona Validity in LLM Agents for Urban Sentiment Perception
-
Mapping the Methodological Space of Classroom Interaction Research: Scale, Duration, and Modality in an Age of AI
-
Revisiting Semantic Role Labeling: Efficient Structured Inference with Dependency-Informed Analysis
-
A multilingual hallucination benchmark: MultiWikiQHalluA
