paper-with-me

Papers

CLMSM: A Multi-Task Learning Framework for Pre-training on Procedural Text

2023-10-22 · Abhilash Nandy, Manav Nitin Kapadnis, Pawan Goyal, Niloy Ganguly

In this paper, we propose CLMSM, a domain-specific, continual pre-training framework, that learns from a large set of procedural recipes. CLMSM uses a Multi-Task Learning Framework to optimize two objectives - a) Contrastive Learning using hard triplets to learn fine-grained differences across entities in the procedures, and b) a novel Mask-Step Modelling objective to learn step-wise context of a procedure. We test the performance of CLMSM on the downstream tasks of tracking entities and aligning actions between two procedures on three datasets, one of which is an open-domain dataset not conforming with the pre-training dataset. We show that CLMSM not only outperforms baselines on recipes (in-domain) but is also able to generalize to open-domain procedural NLP tasks.

📄 PDF Abstract BibTeX arXiv:2310.14326

Code (1)

manavkapadnis/clmsm_emnlp_2023 공식 구현 pytorch

Tasks

Contrastive LearningLanguage ModellingMulti-Task LearningProcedural Text Understanding

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

TAMA: Tool-Augmented Multimodal Agent for Procedural Activity Understanding

2025-09-30 · Kimihiro Hasegawa, Wiradee Imrattanatrai, Masaki Asada, Ken Fukuda 외 arxiv

Procedural activity assistants potentially support humans in a variety of settings, from our daily lives, e.g., cooking or assembling flat-pack furniture, to professional situations, e.g., manufacturing or biological exp…

Multimodal Reasoning

VLA-Pro: Cross-Task Procedural Memory Transfer for Vision-Language-Action Models

2026-05-28 · Shengyu Si, Yuanzhuo Lu, Ruimeng Yang, Ziyi Ye 외 arxiv

Vision-Language-Action~(VLA) models have shown strong potential for general-purpose robotic manipulation, yet they still struggle to generalize to unseen tasks that necessitate transferring relevant experience across obj…

The Unreasonable Effectiveness of VLMs for Zero-shot Procedural Mistake Detection

2026-06-19 · Serdar Ozsoy, Lars Doorenbos, Federico Spurio, Gianpiero Francesca 외 arxiv

Procedural mistake detection is important for quality control and user assistance across many disciplines. Recent work in this field has achieved significant gains by using the reasoning capabilities of Video-Language Mo…

Action Segmentation

Be Consistent! Improving Procedural Text Comprehension using Label Consistency

2019-06-21 · NAACL 2019 6 · Xinya Du, Bhavana Dalvi Mishra, Niket Tandon, Antoine Bosselut 외

Our goal is procedural text comprehension, namely tracking how the properties of entities (e.g., their location) change with time given a procedural text (e.g., a paragraph about photosynthesis, a recipe). This task is c…

Reading Comprehension

LLaPa: A Vision-Language Model Framework for Counterfactual-Aware Procedural Planning

2025-07-11 · Shibo Sun, Xue Li, Donglin Di, Mingjie Wei 외 arxiv

While large language models (LLMs) have advanced procedural planning for embodied AI systems through strong reasoning abilities, the integration of multimodal inputs and counterfactual reasoning remains underexplored. To…