Challenge: Existing efforts to automate wet lab workflows are focusing on graph-prediction models that capture both concrete, exact quantities ("30 minutes") and vague instructions ("swirl")
Approach: They manually annotate PEGs in a corpus of complex lab protocols with a novel interactive textual simulator that keeps track of entity traits and semantic constraints during annotation.
Outcome: The proposed graph-prediction models are good at entity identification and local relation extraction while addressing challenges such as cross-sentence relations and long-range coreference.

Similar Papers

An Annotated Corpus for Machine Reading of Instructions in Wet Lab Protocols (N18-2)

Copied to clipboard

Challenge: Existing efforts to annotate natural language instructions into machine-readable formats are limited.
Approach: They propose to annotate a corpus of natural language instructions consisting of 622 wet lab protocols to facilitate automatic or semi-automatic conversion into a machine-readable format.
Outcome: The proposed corpus can be used to facilitate automatic or semi-automatic conversion of protocols into a machine-readable format and benefit biological research.
End-to-end Parsing of Procedural Text into Flow Graphs (2024.lrec-main)

Copied to clipboard

Challenge: Existing flow graph parsers lack sufficient annotated data to train them . a lack of annotation can cause costly training, and poor flow graph training results in a large improvement.
Approach: They propose a multi-task framework that performs tagging and graph generation simultaneously . they take advantage of the abundance of unlabelled recipes and generate noisy silver annotations .
Outcome: The proposed model can unify the input representation and use compact encoders, resulting in small models with significantly fewer parameters than existing models.
ChemReason-Bench: Benchmarking Large Language Models for Procedural Reasoning in Experimental Chemistry (2026.acl-long)

Copied to clipboard

Challenge: Experimental protocols in organic synthesis specify not only the intended transformation, but also an executable sequence of operations and conditions.
Approach: They propose a human-validated benchmark for verifiable experimental procedure reasoning . they instantiate 7306 benchmark tasks across six complementary formats .
Outcome: The proposed benchmarks show that the evaluations are less diagnostic of procedure-level decision making.
Learning Latent Structures for Cross Action Phrase Relations in Wet Lab Protocols (2021.acl-long)

Copied to clipboard

Challenge: Lack of careful documentation has led to reproducibility crisis in biosciences . wet laboratory protocols are written in natural language and are unclear, composed of disconnected and distant parts and built upon implicit information that were referenced earlier or omitted entirely.
Approach: They propose a model that extracts all action relationships across multiple sentences to generate a MSTG for a given protocol . they propose extending annotations in the WLP corpus for inter-sentence relations and implicit arguments to improve the model's temporal and causal relations.
Outcome: The proposed model achieves an F1 score of 54.53% for temporal and causal relations in protocols from the corpus WLP-MSTG.
API-BLEND: A Comprehensive Corpora for Training and Benchmarking API LLMs (2024.acl-long)

Copied to clipboard

Challenge: Existing methods to train and test large language models that involve calls to tools and APIs are lacking.
Approach: They propose a large corpora for training and systematic testing of tool-augmented LLMs.
Outcome: The proposed datasets mimic real-world scenarios involving API-tasks and slot filling.
BioGraphia: A LLM-Assisted Biological Pathway Graph Annotation Platform (2025.emnlp-demos)

Copied to clipboard

Challenge: Existing methods for obtaining pathway information from biomedical literature rely on simplifying assumptions that limit their ability to capture true complexity of biological reactions.
Approach: They propose a web-based platform to facilitate collaborative pathway graph annotation.
Outcome: The platform supports multi-user collaboration with real-time monitoring, curation, and interactive pathway graph visualization.
A Lightweight Modeling Middleware for Corpus Processing (L18-1)

Copied to clipboard

Challenge: Present-day empirical research in computational or theoretical linguistics has richly annotated and diverse corpus resources.
Approach: They propose a framework for modeling arbitrary multi-modal corpus resources in a unified form for processing tools.
Outcome: The proposed framework allows researchers to explore and query more diverse corpus resources and artifacts through a single interactive interface.
Graph of Trace: Visualizing Execution Traces of Scientific Agents (2026.acl-demo)

Copied to clipboard

Challenge: Scientific AI agents can perform complex research tasks, but these unfolded workflows are difficult for humans to inspect and review, limiting interpretable, controllable and effective human–AI collaboration.
Approach: They propose a monitoring and visualization framework that records fine-grained execution events and organizes them into a directed graph that makes agent workflows explicit as they proceed.
Outcome: The proposed framework records intermediate steps (e.g. tool calls and code executions) and renders them as real-time updated visual traces that expose workflow structure.
PAGED: A Benchmark for Procedural Graphs Extraction from Documents (2024.acl-long)

Copied to clipboard

Challenge: Existing methods for extraction of procedural graphs from documents are not solving the task well.
Approach: They propose a benchmark to test automatic extraction of procedural graphs from documents . they involve three advanced large language models and enhance them with a novel self-refine strategy .
Outcome: The proposed benchmark systematically examines the progress of current methods and explores the potential of emerging large language models (LLMs) on this task.
KCAT: A Knowledge-Constraint Typing Annotation Tool (P19-3)

Copied to clipboard

Challenge: Recent years Natural Language Processing community has seen a surge of interest in fine-grained entity typing (FET) given an entity mention (i.e. a sequence of token spans representing an entity), FET aims at uncovering its contextdependent type.
Approach: They propose an efficient Knowledge Constraint Fine-grained Entity Typing Annotation Tool which further improves the entity typing process through entity linking together with some practical functions.
Outcome: The proposed tool improves the entity typing process by linking the candidate types with some practical functions.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations