@inproceedings{dip-etal-2026-llm4cell,
title = "{LLM}4{C}ell: Taxonomy and Evaluation of {LLM} and Agentic Models for Single-Cell Biology",
author = "Dip, Sajib Acharjee and
Zafor, Adrika and
Paul, Bikash Kumar and
Shuvo, Uddip Acharjee and
Emon, Muhit Islam and
Wang, Xuan and
Zhang, Liqing",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.1942/",
pages = "41913--41954",
ISBN = "979-8-89176-390-6",
abstract = "Large language models (LLMs) and emerging agentic frameworks are beginning to influence single-cell biology by enabling natural-language interfaces, generative annotation, and multimodal data integration. However, progress remains fragmented across data modalities, model families, and evaluation practices. LLM4Cell presents a unified survey of 58 foundation and agentic models developed for single-cell research, spanning RNA, ATAC, multi-omic, and spatial modalities. We organize these methods into five families foundation, text-bridge, spatial/multimodal, epigenomic, and agentic and map them to eight key analytical tasks, including annotation, trajectory inference, perturbation modeling, and drug-response prediction. Drawing on over 40 public datasets, we analyze benchmark coverage, data diversity, and ethical or scalability constraints, and synthesize reported capabilities across ten domain-level dimensions related to biological grounding, multimodal alignment, fairness, privacy, and interpretability. By explicitly linking datasets, modeling paradigms, and evaluation domains, LLM4Cell provides an integrated perspective on language-driven single-cell analysis and highlights open challenges in standardization, interpretability, and trustworthy model development."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dip-etal-2026-llm4cell">
<titleInfo>
<title>LLM4Cell: Taxonomy and Evaluation of LLM and Agentic Models for Single-Cell Biology</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sajib</namePart>
<namePart type="given">Acharjee</namePart>
<namePart type="family">Dip</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adrika</namePart>
<namePart type="family">Zafor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bikash</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Paul</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Uddip</namePart>
<namePart type="given">Acharjee</namePart>
<namePart type="family">Shuvo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhit</namePart>
<namePart type="given">Islam</namePart>
<namePart type="family">Emon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liqing</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>Large language models (LLMs) and emerging agentic frameworks are beginning to influence single-cell biology by enabling natural-language interfaces, generative annotation, and multimodal data integration. However, progress remains fragmented across data modalities, model families, and evaluation practices. LLM4Cell presents a unified survey of 58 foundation and agentic models developed for single-cell research, spanning RNA, ATAC, multi-omic, and spatial modalities. We organize these methods into five families foundation, text-bridge, spatial/multimodal, epigenomic, and agentic and map them to eight key analytical tasks, including annotation, trajectory inference, perturbation modeling, and drug-response prediction. Drawing on over 40 public datasets, we analyze benchmark coverage, data diversity, and ethical or scalability constraints, and synthesize reported capabilities across ten domain-level dimensions related to biological grounding, multimodal alignment, fairness, privacy, and interpretability. By explicitly linking datasets, modeling paradigms, and evaluation domains, LLM4Cell provides an integrated perspective on language-driven single-cell analysis and highlights open challenges in standardization, interpretability, and trustworthy model development.</abstract>
<identifier type="citekey">dip-etal-2026-llm4cell</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.1942/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>41913</start>
<end>41954</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LLM4Cell: Taxonomy and Evaluation of LLM and Agentic Models for Single-Cell Biology
%A Dip, Sajib Acharjee
%A Zafor, Adrika
%A Paul, Bikash Kumar
%A Shuvo, Uddip Acharjee
%A Emon, Muhit Islam
%A Wang, Xuan
%A Zhang, Liqing
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F dip-etal-2026-llm4cell
%X Large language models (LLMs) and emerging agentic frameworks are beginning to influence single-cell biology by enabling natural-language interfaces, generative annotation, and multimodal data integration. However, progress remains fragmented across data modalities, model families, and evaluation practices. LLM4Cell presents a unified survey of 58 foundation and agentic models developed for single-cell research, spanning RNA, ATAC, multi-omic, and spatial modalities. We organize these methods into five families foundation, text-bridge, spatial/multimodal, epigenomic, and agentic and map them to eight key analytical tasks, including annotation, trajectory inference, perturbation modeling, and drug-response prediction. Drawing on over 40 public datasets, we analyze benchmark coverage, data diversity, and ethical or scalability constraints, and synthesize reported capabilities across ten domain-level dimensions related to biological grounding, multimodal alignment, fairness, privacy, and interpretability. By explicitly linking datasets, modeling paradigms, and evaluation domains, LLM4Cell provides an integrated perspective on language-driven single-cell analysis and highlights open challenges in standardization, interpretability, and trustworthy model development.
%U https://aclanthology.org/2026.acl-long.1942/
%P 41913-41954
Markdown (Informal)
[LLM4Cell: Taxonomy and Evaluation of LLM and Agentic Models for Single-Cell Biology](https://aclanthology.org/2026.acl-long.1942/) (Dip et al., ACL 2026)
ACL
- Sajib Acharjee Dip, Adrika Zafor, Bikash Kumar Paul, Uddip Acharjee Shuvo, Muhit Islam Emon, Xuan Wang, and Liqing Zhang. 2026. LLM4Cell: Taxonomy and Evaluation of LLM and Agentic Models for Single-Cell Biology. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 41913–41954, San Diego, California, United States. Association for Computational Linguistics.