Image de couverture de livre

Heterogeneity in Formal Linguistic Competence of Language Models: Is Data the Real Bottleneck?

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Renduchintala, H S V N S Kowndinya, Bhatia, Sumit
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language Artificial Intelligence Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

SMART: Submodular Data Mixture Strategy for Instruction Tuning
par: Renduchintala, H S V N S Kowndinya, et autres
Publié: (2024)

POSIX: A Prompt Sensitivity Index For Large Language Models
par: Chatterjee, Anwoy, et autres
Publié: (2024)

On the Effect of Instruction Tuning Loss on Generalization
par: Chatterjee, Anwoy, et autres
Publié: (2025)

Tied-Lora: Enhancing parameter efficiency of LoRA with weight tying
par: Renduchintala, Adithya, et autres
Publié: (2023)

Between Circuits and Chomsky: Pre-pretraining on Formal Languages Imparts Linguistic Biases
par: Hu, Michael Y., et autres
Publié: (2025)

Language Bottleneck Models for Qualitative Knowledge State Modeling
par: Berthon, Antonin, et autres
Publié: (2025)

Consistency Is the Key: Detecting Hallucinations in LLM Generated Text By Checking Inconsistencies About Key Facts
par: Gupta, Raavi, et autres
Publié: (2025)

Perceptions of Linguistic Uncertainty by Language Models and Humans
par: Belem, Catarina G, et autres
Publié: (2024)

Linguistic Blind Spots of Large Language Models
par: Cheng, Jiali, et autres
Publié: (2025)

Policy Learning with a Language Bottleneck
par: Srivastava, Megha, et autres
Publié: (2024)

Are Small Language Models Ready to Compete with Large Language Models for Practical Applications?
par: Sinha, Neelabh, et autres
Publié: (2024)

Uncovering Competency Gaps in Large Language Models and Their Benchmarks
par: Bohacek, Maty, et autres
Publié: (2025)

Regurgitative Training: The Value of Real Data in Training Large Language Models
par: Zhang, Jinghui, et autres
Publié: (2024)

LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety
par: Yang, Junxiao, et autres
Publié: (2026)

ABBEL: LLM Agents Acting through Belief Bottlenecks Expressed in Language
par: Lidayan, Aly, et autres
Publié: (2025)

Mixture of Heterogeneous Grouped Experts for Language Modeling
par: Ma, Zhicheng, et autres
Publié: (2026)

Exploring RL-based LLM Training for Formal Language Tasks with Programmed Rewards
par: Padula, Alexander G., et autres
Publié: (2024)

Towards Real-world Human Behavior Simulation: Benchmarking Large Language Models on Long-horizon, Cross-scenario, Heterogeneous Behavior Traces
par: Chen, Jiawei, et autres
Publié: (2026)

FVEL: Interactive Formal Verification Environment with Large Language Models via Theorem Proving
par: Lin, Xiaohan, et autres
Publié: (2024)

Concurrent Linguistic Error Detection (CLED): a New Methodology for Error Detection in Large Language Models
par: Zhu, Jinhua, et autres
Publié: (2024)

Experience Sharing in Mutual Reinforcement Learning for Heterogeneous Language Models
par: Liu, Xiaoze, et autres
Publié: (2026)

BIPEFT: Budget-Guided Iterative Search for Parameter Efficient Fine-Tuning of Large Pretrained Language Models
par: Chang, Aofei, et autres
Publié: (2024)

IndicSentEval: How Effectively do Multilingual Transformer Models encode Linguistic Properties for Indic Languages?
par: Aravapalli, Akhilesh, et autres
Publié: (2024)

AraLingBench A Human-Annotated Benchmark for Evaluating Arabic Linguistic Capabilities of Large Language Models
par: Zbeeb, Mohammad, et autres
Publié: (2025)

Towards a Theoretical Understanding of Synthetic Data in LLM Post-Training: A Reverse-Bottleneck Perspective
par: Gan, Zeyu, et autres
Publié: (2024)

Artificial Conversations, Real Results: Fostering Language Detection with Synthetic Data
par: Mohammadi, Fatemeh, et autres
Publié: (2025)

Safe: Enhancing Mathematical Reasoning in Large Language Models via Retrospective Step-aware Formal Verification
par: Liu, Chengwu, et autres
Publié: (2025)

Marco-o1 v2: Towards Widening The Distillation Bottleneck for Reasoning Models
par: Yin, Huifeng, et autres
Publié: (2025)

FormalProofBench: Can Models Write Graduate Level Math Proofs That Are Formally Verified?
par: Ravi, Nikil, et autres
Publié: (2026)

Deception Detection from Linguistic and Physiological Data Streams Using Bimodal Convolutional Neural Networks
par: Li, Panfeng, et autres
Publié: (2023)

Pooling Attention: Evaluating Pretrained Transformer Embeddings for Deception Classification
par: Mamtani, Sumit, et autres
Publié: (2025)

Efficient Real-time Refinement of Language Model Text Generation
par: Ko, Joonho, et autres
Publié: (2025)

Formal-LLM: Integrating Formal Language and Natural Language for Controllable LLM-based Agents
par: Li, Zelong, et autres
Publié: (2024)

LexC-Gen: Generating Data for Extremely Low-Resource Languages with Large Language Models and Bilingual Lexicons
par: Yong, Zheng-Xin, et autres
Publié: (2024)

Lean-ing on Quality: How High-Quality Data Beats Diverse Multilingual Data in AutoFormalization
par: Chan, Willy, et autres
Publié: (2025)

Linguistic Calibration of Long-Form Generations
par: Band, Neil, et autres
Publié: (2024)

Sectoral Coupling in Linguistic State Space
par: Dumbrava, Sebastian
Publié: (2025)

Scaling Data-Constrained Language Models
par: Muennighoff, Niklas, et autres
Publié: (2023)

RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models
par: Jin, Zhuoran, et autres
Publié: (2024)

RealCritic: Towards Effectiveness-Driven Evaluation of Language Model Critiques
par: Tang, Zhengyang, et autres
Publié: (2025)