20 results for “Knowledge of Large Language Models”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
The paper proposes Large Language Gibbs, a scheme for structured probabilistic inference using conditional distributions of large language models as transition operators.
The paper introduces Mental Model Management (3M), a framework for representing knowledge as compact mental models and continuously integrating new information.
This paper evaluates the performance of large language models on quiz-style questions covering common and niche topics in six European languages, finding significant knowledge gaps and language-depend…
Wanying Ren, Xin Song, Futing Wang, Guoxiu He +1 more
The paper theoretically analyzes the limitations of parameter-based knowledge editing and empirically demonstrates that these methods consistently damage core LLM capabilities compared to retrieval-ba…
The paper tests language models on an information retrieval task using the Wikipedia Game and compares their performance across languages and domains.
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…
This paper surveys 34 peer-reviewed studies applying generative large language models to literature retrieval and eligibility screening.
This paper introduces a novel evaluation framework for Large Language Models using pairwise comparisons and Elo rating system.
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.
ProbScale is a novel framework that combines neural scaling laws and language model probing to identify highly efficient, task-specific subnetworks within pre-trained Small Language Models, achieving…
Junhyuck Kim, Jihun Yun, Haechan Kim, Gyeongman Kim +2 more
The paper introduces a systematic framework to convert large Mixture-of-Experts (MoE) models into memory-efficient, fully dense architectures, achieving superior performance compared to traditional pr…
Yiming Zhang, Zhonghan Zhao, Wenwei Zhang, Haiteng Zhao +12 more
This paper presents the benefits of visual pretraining for foundation model intelligence, outperforming text-only pretraining on multiple backbones and benchmarks.
The paper introduces MORFES, a benchmark for evaluating inflectional competence of language models on Modern Greek, and evaluates several open language models on it.
Jiarui Feng, Hanqing Zeng, Karish Grover, Ruizhong Qiu +10 more
The paper proposes DAG-MoE, a novel sparse Mixture-of-Experts framework that replaces standard weighted-sum aggregation with structural aggregation to enhance model performance and enable multi-step r…
Ghadir Alselwi, Basem Suleiman, Hao Xue, Shoaib Jameel +3 more
This paper introduces KGERMAR, a framework that constructs dynamic, context-specific knowledge graphs during inference for long-context language modeling, achieving lower perplexity and better memory…
This paper discusses the current understanding of Large Language Models (LLMs), their capabilities, and their relationship to human cognition, with a focus on emerging capabilities and mechanistic imp…