paper-with-me

홈 › Papers

Analysis and Explainability of LLMs Via Evolutionary Methods

2026-04-27 · Shannon K. Gallagher, Swati Rallapalli, Tyler Brooks, Chuck Loughin, Michele Sezgin, Ronald Yurko arxiv

Evolutionary methods have long been useful for analysis and explanation in genetics, biology, ecology, and related fields. In this work, we extend these methods to neural networks, specifically large language models (LLMs), to better analyze and explain relationships among models. We show how relating weights to genotypes and output text to phenotypes can improve our understanding of model lineage, important datasets, the roles of different model layers, and visualization of model relationships. We demonstrate this in a controlled experiment, where our estimated evolutionary trees reliably recover the topology of the ground-truth training tree. We further identify the most important weight layers according to weight differences and show through phenotypic experiments that one training dataset appears to contribute more useful information than the others. Finally, we generate an unsupervised evolutionary tree of black-box foundation models. Throughout, we provide visualizations that support a clearer understanding of evolutionary relationships among LLMs.

📄 PDF Abstract BibTeX arXiv:2605.02930

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Through a Compressed Lens: Investigating the Impact of Quantization on LLM Explainability and Interpretability

2025-05-20 · Qianli Wang, Mingyang Wang, Nils Feldhus, Simon Ostermann 외

Quantization methods are widely used to accelerate inference and streamline the deployment of large language models (LLMs). While prior research has extensively investigated the degradation of various LLM capabilities du…

counterfactualMemorizationQuantization

Evolutionary Computation and Large Language Models: A Survey of Methods, Synergies, and Applications

2025-05-21 · Dikshit Chauhan, Bapi Dutta, Indu Bala, Niki van Stein 외

Integrating Large Language Models (LLMs) and Evolutionary Computation (EC) represents a promising avenue for advancing artificial intelligence by combining powerful natural language understanding with optimization and se…

Evolutionary AlgorithmsNatural Language UnderstandingPrompt EngineeringSurvey

Thoughts without Thinking: Reconsidering the Explanatory Value of Chain-of-Thought Reasoning in LLMs through Agentic Pipelines

2025-05-01 · Ramesh Manuvinakurike, Emanuel Moss, Elizabeth Anne Watkins, Saurav Sahay 외

Agentic pipelines present novel challenges and opportunities for human-centered explainability. The HCXAI community is still grappling with how best to make the inner workings of LLMs transparent in actionable ways. Agen…

Performance and Explainability Requirements of Evolutionary Algorithms in Real-World Physics-Informed Optimization

2026-05-27 · Helena Stegherr, Michael Heider, Nils Meyer, Tobias Thummerer 외 arxiv

Evolutionary computation offers a variety of tools to solve complex real-world optimization problems. However, research often focuses on smaller, simplified problems and optimization algorithms that sometimes miss expect…

Monetizing Currency Pair Sentiments through LLM Explainability

2024-07-29 · Lior Limonad, Fabiana Fournier, Juan Manuel Vera Díaz, Inna Skarbovsky 외

Large language models (LLMs) play a vital role in almost every domain in today's organizations. In the context of this work, we highlight the use of LLMs for sentiment analysis (SA) and explainability. Specifically, we c…

Sentiment Analysis