Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 28 for “"Language Reasoning"”.
-
Enhancing competitive-level code generation by utilizing natural language reasoning
Large language models have substantially advanced automatic code generation, but competitive programming remains a demanding test of their reasoning abilities. Solving these problems requires more than producing syntactically valid code: a model must abstract a narrative specification into its …
-
Statistical Inference for Image Classification, Language Reasoning, and Counterfactual Estimation
… and reliable confidence estimation for large language models. The first contribution introduces DPI-RG, a distribution-free framework for constructing predictive sets for high-dimensional data under distribution shifts. Using a conditional Wasserstein round-trip generative model, DPI-RG maps …
-
Natural Language Reasoning on ALC knowledge bases using Large Language Models
Τα προεκπαιδευμένα γλωσσικά μοντέλα έχουν κυριαρχήσει στην επεξεργασία φυσικής γλώσσας, αποτελώντας πρόκληση για τη χρήση γλωσσών αναπαράστασης γνώσης για την περιγραφή του κόσμου. Ενώ οι γλώσσες αυτές δεν είναι αρκετά εκφραστικές για να καλύψουν πλήρως τη φυσική γλώσσα, τα γλωσσικά μοντέλα έχουν …
-
ADVANCED DIFFUSION ROBOT MANIPULATION POLICIES FOR LANGUAGE REASONING, LONG-HORIZON PLANNING, AND SKILL ABSTRACTION
… semantics, hierarchy, and skills. DISCO grounds language by converting instructions and multi-view observations into 3D task-level keyframes with vision-language models, then guides an unconditional diffusion policy through constrained inpainting to improve zero-shot instruction following despite …
-
Language Reasoning and Verbal Reasoning Difficulties of Students in the four year BSc-Course at NWU
… science need to use specialized conceptual language in reading, reasoning and problem solving. This study explored the language used in chemistry including non-technical words (i.e., understanding of their meanings in both scientific and everyday contexts), and verbal reasoning skills (i.e., …
-
Learning to Reason over Natural Language via Accessing Diverse Knowledge Resources
Reasoning is the capability of drawing new conclusions from existing information or knowledge, and it has been a central topic in artificial intelligence. Developing intelligent systems that are capable of understanding natural language input and reasoning to produce conclusions is highly desirable …
-
The relationship between preschoolers' academic self-esteem and the quality of their child care center.
… subscales of interaction, parents and staff and language-reasoning.
-
An Evaluation of in-Service Training in a Day Care Program
… Care Routines, (2) Furnishings and Display, (3) Language Reasoning Experiences, (4) Fine and Gross Motor Activities, (5) Creative Activities, (6) Social Development, and (7) Adult Needs. The average scores from the three raters were derived to establish a profile of each classroom thus …
-
Differences in Early Childhood Environmental Rating Scale Scores in Collaborative and Non-Collaborative West Virginia Pre-K Classrooms located in Child Care Facilities
… Space and Furnishings, Personal Care Routines, Language-Reasoning, Activities, Interaction, Program Structure, and Parents and Staff. Thirty-six pre-k collaborative programs participated and 136 non-collaborative programs participated in the study. Non-collaborative pre-k classrooms had lower …
-
A Neuro-Symbolic Approach to Vision, Language, and Multi-Modal Reasoning
… medicine. With advances in foundation models for language, image, and multi-modal data, it is becoming feasible for end users to accomplish complex tasks that would otherwise require substantial domain expertise, engineered pipelines, and resources. Yet the capabilities of today's foundation …
-
Neurosymbolic Programming in Scallop: Design, Implementation, and Applications
… worlds of deep learning and symbolic reasoning. It thereby enables more accurate, interpretable, and domain-aware AI solutions that surpass purely neural or symbolic approaches. While significant advances have been made in domain-specific neurosymbolic methods, the field lacks a …
-
Towards a Theory and Practice of Open-Ended Reasoning with Generative Models
The unreasonable effectiveness of large language modeling has enabled the rapid development of generative systems capable of increasingly sophisticated ''human-like'' reasoning. This impressive performance stems largely from two key factors: 1. A high-quality pre-training phase during which models …
-
Object-wise metric distance estimation from a single RGB image via semantic and geometric reasoning
… remains scale-ambiguous, or use implicit vision-language reasoning that can be unstable for precise measurement. This thesis proposes a semantic–geometric pipeline for recovering metric scale by combining open-vocabulary object grounding and segmentation, label normalization, monocular depth, and …
-
Harmonizing Divergence in Computational Discourse Analysis
… from surface-level text processing to deeper language reasoning, as it captures the logical flow of ideas that shapes meaning into a coherent text. However, progress in computational discourse analysis is hindered by divergent theoretical frameworks, ambiguity in implicit discourse relations …
-
Logical representations for automated reasoning about spatial relationships
… logical representations for describing and reasoning about spatial situations. Previously proposed theories of spatial regions are investigated in some detail - especially the 1st-order theory of Randell, Cui and Cohn (1992). The difficulty of achieving effective automated reasoning with …
-
The Effects of an Intervention That Includes In-Class Coaching on Preschool Teachers and Children
… a measure of teacher-child interactions and language-reasoning were not significantly changed. An ANOVA indicated no significant differences in kindergarten school readiness scores between centers that received coaching for varying amounts of time. Teachers were interviewed to discover their …
-
The generation of academic discourse by ESL learners through computer-based peer tutoring; a case study
… (1991) concepts of conversational and academic language proficiency, and Halliday’s (1985) model of language socialization distinguishing interpersonal, ideational and textual components; and followed Staab (1986), in dividing the ideational component into “Informing” and “Reasoning”. In PT( 1) …
-
Explainable Multi-Step Reasoning Over Natural Language
Despite the significant progress of reasoning over natural language in the recent years, multi-step natural language reasoning is still a great challenge to the current algorithms. The challenges come from three aspects. First, some multi-step reasoning problems require the retrieval of evidence …
-
Assignment Calculus: A Pure Imperative Reasoning Language
… this thesis, we undertake a study of imperative reasoning. Beginning with a philosophical analysis of the distinction between imperative and functional language features, we define a (pure) imperative language as one whose constructs are inherently referentially opaque. We then give a definition …
-
Causality, identifiability, and representation learning for machine learning with non-i.i.d. data
… accuracy, and demonstrating advanced natural language reasoning. Their capabilities keep improving as compute, data and model size scale, captured by empirical scaling laws. However, these capabilities are typically evaluated on held-out test sets assumed independent and identically …
Page 1 of 2