20 results for “Language models”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
The paper introduces a new quantitative metric, Contextual Alternative Choice (CAC), to rigorously test language models' syntactic and functional understanding of determiners, showing that current mod…
The paper tests language models on an information retrieval task using the Wikipedia Game and compares their performance across languages and domains.
This paper evaluates the performance of twelve Small Language Models on Arabic natural language processing tasks.
The paper proposes EPIC, an efficient and parallel decoding framework that significantly speeds up the process of constraining diffusion language model outputs using Context-Free Grammars (CFG).
Minhua Lin, Zijun Wang, Zewen Liu, Zhaotian Weng +6 more
This paper proposes a method, LM2LM, to train large language models to generate effective improvement proposals using reinforcement learning and a research world model.
The paper argues that large language models (LLMs) are a special case of world models and proposes a continuous spectrum between token prediction and latent-space architectures.
Zhilin Guo, Boqiao Zhang, Hakan Aktas, Kyle Fogarty +13 more
This paper introduces a Telescopic Language Model (TLM) that can serve multiple compute budgets with a single training run.
The paper introduces PortBERT, a family of RoBERTa-based language models for Portuguese, which achieves competitive performance while explicitly balancing efficiency and accuracy.
This paper introduces a pipeline to extract grammatical rules, example sentences, and lexicons from grammar books and generates synthetic parallel corpora for fine-tuning machine translation models on…
The paper proposes Large Language Gibbs, a scheme for structured probabilistic inference using conditional distributions of large language models as transition operators.
This paper investigates the performance of small language models in relation extraction tasks, showing that task-specific adaptation can enable them to outperform larger, general-purpose models.
Kevin Cheang, Geoff Hulette, Rahul Kumar, Felipe R. Monteiro +4 more
An agent called Autogrammar is introduced to automatically learn context-free grammars for domain-specific languages, enabling grammar-constrained decoding and improving language model performance.
The paper introduces MIDI, a novel multilingual dataset that embeds idioms in realistic sentence and conversational contexts across diverse resource levels, revealing that idiom comprehension is signi…
This paper proposes Chained Recursive Language Models (Chained RLM), an inference-time architecture for managing context in large language models, allowing for intermediate artifacts to be inspected,…
This paper analyzes speech-text interleaved language models and reveals that they go through an implicit transcription phase in which spoken words become decodable as text in intermediate layers.
This paper introduces a novel evaluation framework for Large Language Models using pairwise comparisons and Elo rating system.
The paper introduces Mental Model Management (3M), a framework for representing knowledge as compact mental models and continuously integrating new information.
The paper introduces MORFES, a benchmark for evaluating inflectional competence of language models on Modern Greek, and evaluates several open language models on it.
The paper proposes an aggressive, parameter-efficient method to prune non-essential experts from Mixture-of-Experts (MoE) LLMs, significantly compressing the model while maintaining high machine trans…