Copertina

Meaning-infused grammar: Gradient Acceptability Shapes the Geometric Representations of Constructions in LLMs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Rakshit, Supantho, Goldberg, Adele
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language Artificial Intelligence 68T50
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

One SPACE to Rule Them All: Jointly Mitigating Factuality and Faithfulness Hallucinations in LLMs
di: Wang, Pengbo, et al.
Pubblicazione: (2025)

Acceptable Use Policies for Foundation Models
di: Klyman, Kevin
Pubblicazione: (2024)

LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations
di: Orgad, Hadas, et al.
Pubblicazione: (2024)

For GPT-4 as with Humans: Information Structure Predicts Acceptability of Long-Distance Dependencies
di: Cuneo, Nicole, et al.
Pubblicazione: (2025)

LLMs as Deceptive Agents: How Role-Based Prompting Induces Semantic Ambiguity in Puzzle Tasks
di: Yoo, Seunghyun
Pubblicazione: (2025)

OPENXRD: A Comprehensive Benchmark Framework for LLM/MLLM XRD Question Answering
di: Vosoughi, Ali, et al.
Pubblicazione: (2025)

HInter: Exposing Hidden Intersectional Bias in Large Language Models
di: Souani, Badr, et al.
Pubblicazione: (2025)

Pay Attention to What You Need
di: Gao, Yifei, et al.
Pubblicazione: (2023)

EvidenceMap: Learning Evidence Analysis to Unleash the Power of Small Language Models for Biomedical Question Answering
di: Zong, Chang, et al.
Pubblicazione: (2025)

T-VEC: A Telecom-Specific Vectorization Model with Enhanced Semantic Understanding via Deep Triplet Loss Fine-Tuning
di: Ethiraj, Vignesh, et al.
Pubblicazione: (2025)

Auto prompt sql: a resource-efficient architecture for text-to-sql translation in constrained environments
di: Tang, Zetong, et al.
Pubblicazione: (2025)

Japanese Tort-case Dataset for Rationale-supported Legal Judgment Prediction
di: Yamada, Hiroaki, et al.
Pubblicazione: (2023)

Crossing Linguistic Horizons: Finetuning and Comprehensive Evaluation of Vietnamese Large Language Models
di: Truong, Sang T., et al.
Pubblicazione: (2024)

Curriculum Recommendations Using Transformer Base Model with InfoNCE Loss And Language Switching Method
di: Xu, Xiaonan, et al.
Pubblicazione: (2024)

A Primer on Large Language Models and their Limitations
di: Johnson, Sandra, et al.
Pubblicazione: (2024)

Do LLMs have a Gender (Entropy) Bias?
di: Prabhune, Sonal, et al.
Pubblicazione: (2025)

Pun Unintended: LLMs and the Illusion of Humor Understanding
di: Zangari, Alessandro, et al.
Pubblicazione: (2025)

SpokenNativQA: Multilingual Everyday Spoken Queries for LLMs
di: Alam, Firoj, et al.
Pubblicazione: (2025)

Give it Space! Explicit Disentangling of Positional and Semantic Representations in Encoders
di: Lequeu, Pierre-Antoine, et al.
Pubblicazione: (2026)

Evaluating Embedding Generalization: How LLMs, LoRA, and SLERP Shape Representational Geometry
di: Kabane, Siyaxolisa
Pubblicazione: (2025)

Learning When to Think: Shaping Adaptive Reasoning in R1-Style Models via Multi-Stage RL
di: Tu, Songjun, et al.
Pubblicazione: (2025)

The Personalization Trap: How User Memory Alters Emotional Reasoning in LLMs
di: Fang, Xi, et al.
Pubblicazione: (2025)

MORABLES: A Benchmark for Assessing Abstract Moral Reasoning in LLMs with Fables
di: Marcuzzo, Matteo, et al.
Pubblicazione: (2025)

Task Complexity Matters: An Empirical Study of Reasoning in LLMs for Sentiment Analysis
di: Huang, Donghao, et al.
Pubblicazione: (2026)

Cognitive Workspace: Active Memory Management for LLMs -- An Empirical Study of Functional Infinite Context
di: An, Tao
Pubblicazione: (2025)

UnifiedCrawl: Aggregated Common Crawl for Affordable Adaptation of LLMs on Low-Resource Languages
di: Tessema, Bethel Melesse, et al.
Pubblicazione: (2024)

ADE: Adaptive Dictionary Embeddings -- Scaling Multi-Anchor Representations to Large Language Models
di: Demirci, Orhan, et al.
Pubblicazione: (2026)

LLM-Assisted Crisis Management: Building Advanced LLM Platforms for Effective Emergency Response and Public Collaboration
di: Otal, Hakan T., et al.
Pubblicazione: (2024)

Evaluating LLMs for Historical Document OCR: A Methodological Framework for Digital Humanities
di: Levchenko, Maria
Pubblicazione: (2025)

Forging GEMs: Advancing Greek NLP through Quality-Based Corpus Curation
di: Apostolopoulou, Alexandra, et al.
Pubblicazione: (2025)

Number Representations in LLMs: A Computational Parallel to Human Perception
di: AlquBoj, H. V., et al.
Pubblicazione: (2025)

WASIL: In-the-Wild Arabic Spoken Interactions with LLMs
di: Ali, Zien Sheikh, et al.
Pubblicazione: (2026)

A Language Model-Driven Semi-Supervised Ensemble Framework for Illicit Market Detection Across Deep/Dark Web and Social Platforms
di: Yazdanjue, Navid, et al.
Pubblicazione: (2025)

Semantic Needles in Document Haystacks: Sensitivity Testing of LLM-as-a-Judge Similarity Scoring
di: Aksoy, Sinan G., et al.
Pubblicazione: (2026)

Quantifying Fairness in LLMs Beyond Tokens: A Semantic and Statistical Perspective
di: Xu, Weijie, et al.
Pubblicazione: (2025)

The Meta-Prompting Protocol: Orchestrating LLMs via Adversarial Feedback Loops
di: Fu, Fanzhe
Pubblicazione: (2025)

Measuring Faithfulness and Abstention: An Automated Pipeline for Evaluating LLM-Generated 3-ply Case-Based Legal Arguments
di: Zhang, Li, et al.
Pubblicazione: (2025)

The Illusion of Role Separation: Hidden Shortcuts in LLM Role Learning (and How to Fix Them)
di: Wang, Zihao, et al.
Pubblicazione: (2025)

SVDq: 1.25-bit and 410x Key Cache Compression for LLM Attention
di: Yankun, Hong, et al.
Pubblicazione: (2025)

Mediator: Memory-efficient LLM Merging with Less Parameter Conflicts and Uncertainty Based Routing
di: Lai, Kunfeng, et al.
Pubblicazione: (2025)