Papers with CPT
CharacterGPT: A Persona Reconstruction Framework for Role-Playing Agents (2025.naacl-industry)
Copied to clipboard
| Challenge: | Maintaining consistent character personas remains a significant challenge due to variability in information extraction. |
| Approach: | They propose a framework to dynamically reconstruct character personas through Character Persona Training. |
| Outcome: | The proposed framework is evaluated through Big Five personality evaluations and creative tasks, in which characters generate original narratives. |
Efficient Continual Pre-training of LLMs for Low-resource Languages (2025.naacl-industry)
Copied to clipboard
| Challenge: | Open-source large language models (LLMs) are a promising tool for low-resource languages . however, there is still a substantial performance gap between high-resourced languages and LRLs . |
| Approach: | They develop an algorithm to select a subset of texts from a larger corpus and use it to select tokens for LLMs. |
| Outcome: | The proposed algorithm reduces the cost of continual pre-training (CPT) with large amounts of language-specific data. |
TELLME: Test-Enhanced Learning for Language Model Enrichment (2026.findings-eacl)
Copied to clipboard
Minjun Kim, Inho Won, HyeonSeok Lim, MinKyu Kim, Junghun Yuk, Wooyoung Go, Jongyoul Park, Jungyeul Park, KyungTae Lim
| Challenge: | Continual pre-training (CPT) has been widely adopted as a method for domain expansion in large language models, but has faced challenges such as acquiring large-scale domain-specific datasets and high computational costs. |
| Approach: | They propose a method that integrates the Test-Enhanced Learning principle with CPT to promote efficient domain-specific knowledge acquisition and long-term memory retention. |
| Outcome: | The proposed method outperforms existing methods by 23.6% in the financial domain and achieves 9.8% improvement in long-term memory retention. |
Taming the Real-world Complexities in CPT E/M Coding with Large Language Models (2025.emnlp-industry)
Copied to clipboard
Islam Nassar, Yang Lin, Yuan Jin, Rongxin Zhu, Chang Wei Tan, Zenan Zhai, Nitika Mathur, Thanh Tien Vu, Xu Zhong, Long Duong, Yuan-Fang Li
| Challenge: | Evaluation and Management (E/M) coding is performed by physicians and trained human coders who review clinical encounter notes and electronic health record data to assign appropriate codes. |
| Approach: | They propose a framework that automates evaluation and management coding tasks using the Current Procedural Terminology (CPT) taxonomy. |
| Outcome: | The proposed framework achieves an increase in coding accuracy of more than 36% over a commercial CPT E/M coding system and almost 5% over our strongest single-prompt baseline. |
How to Train a Real-World Silicon Concierge? Internalizing Complex Business Workflow to Only OneModel (2026.acl-industry)
Copied to clipboard
| Challenge: | Traditional industrial agents rely on modular workflows that fracture into a labyrinth of ad-hoc patches, leading to cascading errors and high latency. |
| Approach: | They propose a paradigm shift from external workflows to internalized knowledge representation that consolidates complex business logic and SOPs directly into the model’s parameters. |
| Outcome: | The proposed model breaks the impossible triangle of latency, accuracy, and complexity. |
PlanGPT-VL: Enhancing Urban Planning with Domain-Specific Vision-Language Models (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Existing Vision-Language Models (VLMs) fail to analyze planning maps . specialized visual representations of land use zones, transportation networks, and development policies are needed to interpret complex planning maps. |
| Approach: | They propose a domain-specific VLM tailored for urban planning maps that employs three innovations: PlanAnno-V framework for high-quality VQA data synthesis, Critical Point Thinking (CPT) and PlanBench-V benchmark for systematic evaluation. |
| Outcome: | The new model outperforms general-purpose VLMs on planning map interpretation tasks. |
Continual Mixed-Language Pre-Training for Extremely Low-Resource Neural Machine Translation (2021.findings-acl)
Copied to clipboard
| Challenge: | a lack of data in low-resource languages has limited the performance of a multilingual pre-trained model. |
| Approach: | They propose a continuous pre-training framework to adapt mBART to unseen languages . they construct noisy mixed-language text from the monolingual corpus of the target language . |
| Outcome: | The proposed framework improves finetuning performance on low-resource translation pairs . the proposed framework also improves on translation pairs where both languages are seen . |
Continued Pretraining and Interpretability-Based Evaluation for Low-Resource Languages: A Galician Case Study (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in large language models have led to remarkable improvements in language understanding and text generation. |
| Approach: | They propose a framework to evaluate large language models for underrepresented languages . they examine CPT strategies for languages with limited representation in multilingual models . |
| Outcome: | The proposed evaluation framework is based on the case of Galician language . it assesses trade-offs between linguistic enrichment and task-solving capabilities . |
AfriqueLLM: How Data Mixing and Model Architecture Impact Continued Pre-training for African Languages (2026.acl-long)
Copied to clipboard
Hao Yu, Tianyi Xu, Michael A. Hedderich, Wassim Hamidouche, Syed Waqas Zamir, David Ifeoluwa Adelani
| Challenge: | Continued pretraining (CPT) is a practical route to language adaptation, but improvements on demanding capabilities such as mathematical reasoning are limited. |
| Approach: | They propose to use CPT to adapt large language models to African languages . they use math, code, and synthetic translated data to analyze their models . |
| Outcome: | The proposed models improve on multilingual benchmarks and document-level translation. |
Continually Detection, Rapidly React: Unseen Rumors Detection Based on Continual Prompt-Tuning (2022.coling-1)
Copied to clipboard
| Challenge: | Existing rumor detection models assume the same training and testing distributions and can not cope with the continuously changing social network environment. |
| Approach: | They propose a Continual Prompt-Tuning RD framework which avoids catastrophic forgetting of upstream tasks during sequential task learning and enables bidirectional knowledge transfer between domain tasks. |
| Outcome: | The proposed framework avoids catastrophic forgetting (CF) of upstream tasks during sequential task learning and enables bidirectional knowledge transfer between domain tasks. |
Towards Effective and Efficient Continual Pre-training of Large Language Models (2025.acl-long)
Copied to clipboard
Jie Chen, Zhipeng Chen, Jiapeng Wang, Kun Zhou, Yutao Zhu, Jinhao Jiang, Yingqian Min, Xin Zhao, Zhicheng Dou, Jiaxin Mao, Yankai Lin, Ruihua Song, Jun Xu, Xu Chen, Rui Yan, Zhewei Wei, Di Hu, Wenbing Huang, Ji-Rong Wen
| Challenge: | Continual pre-training (CPT) has been an important approach for adapting language models to specific domains or tasks. |
| Approach: | They propose a Continual pre-training method that can greatly improve Chinese language ability and scientific reasoning ability of LLMs. |
| Outcome: | The proposed method can greatly improve Chinese language ability and scientific reasoning ability of LLMs. |
Breaking Language Barriers: Cross-Lingual Continual Pre-Training at Scale (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have made significant strides towards Artificial General Intelligence, but training them from scratch is prohibitively expensive. |
| Approach: | They propose to continuously pre-train LLMs from existing pre-trained LLM models by using a set of parameters instead of randomly initializing them. |
| Outcome: | The proposed approach saves significant resources and accelerates convergence and performance. |
Continual Training of Language Models for Few-Shot Learning (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent work on applying large language models (LMs) achieves impressive performance in many NLP applications. |
| Approach: | They propose to continuously post-train an LM with unlabeled domains to expand its knowledge without forgetting previous skills. |
| Outcome: | The proposed system improves few-shot end-task learning in these domains. |
A Two-Stage Adaptation of Large Language Models for Text Ranking (2024.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in pre-trained language models (PLMs) have significantly improved ranking performance in text ranking tasks. |
| Approach: | They propose a two-stage progressive paradigm to better adapt LLMs to text ranking by conducting continual pre-training on a large weakly-supervised corpus and performing SFT on high-quality data. |
| Outcome: | The proposed approach outperforms previous methods on in- and out-domain scenarios. |
A Learning Rate Path Switching Training Paradigm for Version Updates of Large Language Models (2024.emnlp-main)
Copied to clipboard
Zhihao Wang, Shiyu Liu, Jianheng Huang, Wang Zheng, YiXuan Liao, Xiaoxin Chen, Junfeng Yao, Jinsong Su
| Challenge: | Version updates are an indispensable requirement for Large Language Models . a large learning rate in the first stage and a complete learning decay process are crucial for version updates of LLMs. |
| Approach: | They propose a learning rate path switching training paradigm for version updates of Large Language Models. |
| Outcome: | The proposed paradigm reduces training cost to 58% when training four versions of LLMs compared to PTFS and CPT . |
CMR Scaling Law: Predicting Critical Mixture Ratios for Continual Pre-training of Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) excel in diverse tasks but often underperform in specialized fields due to limited domain-specific or proprietary corpus. |
| Approach: | They propose a power-law relationship between loss, mixture ratio, and training tokens scale and formalize the trade-off between general and domain-specific capabilities. |
| Outcome: | The proposed model achieves the desired domain transfer while maintaining general ability and highest utilization of available resources. |
Embedding Domain Knowledge for Large Language Models via Reinforcement Learning from Augmented Generation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to embed knowledge into large language models have some limitations . static nature of training data and lack of knowledge in domains create knowledge gaps . |
| Approach: | They propose a method that iteratively cycles between sampling generations and optimizing the model through calculated rewards. |
| Outcome: | The proposed method outperforms baseline approaches on medical, legal, astronomy, and current events datasets. |
Perplexity-Aware Data Scaling Law: Perplexity Landscapes Predict Performance for Continual Pre-training (2026.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have impressive capabilities across a wide range of domains, but their generalpurpose pre-training objectives often leave them illsuited for specialized applications such as healthcare. |
| Approach: | They propose a perplexity-aware data scaling law that establishes a predictive relationship between the perplexities of domain-specific data and the test loss. |
| Outcome: | Experiments on medical and general-domain benchmarks show that the proposed scaling law consistently identifies near-optimal training subsets with significantly reduced data consumption. |
How Personality Traits Shape LLM Risk-Taking Behaviour (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models are increasingly used as autonomous agents for simulation and decision-making. |
| Approach: | They apply Cumulative Prospect Theory and the Big Five personality framework to investigate the relationship between LLMs’ personality traits and risk-propensity. |
| Outcome: | The proposed models show that they are risk-neutral rational agents, whereas others show lower neuroticism and higher conscientiousness and Agreeability traits. |
Data-Efficient Selection via Grammatical Complexity in Continual Pre-training of Domain-Specific LLMs (2025.emnlp-main)
Copied to clipboard
Yizhou Ying, Geng Zhang, Cui Danxin, Chengyu Du, Guanglei Yue, Sihang Jiang, Jiaqing Liang, Yifei Fu, Hailin Hu, Yanghua Xiao
| Challenge: | Existing data selection strategies for continual pre-training of large language models often rely on scarce labeled data or computationally expensive LLMs. |
| Approach: | They propose an annotation-independent data selection framework for CPT that evaluates grammatical complexity using lexical diversity and syntactic complexity. |
| Outcome: | The proposed framework outperforms baselines on a financial dataset and surpasses full-data training by 1.7% using only 20% of the data. |
Synthetic Knowledge Ingestion: Towards Knowledge Refinement and Injection for Enhancing Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models capture factual knowledge across a wide range of domains, but refining their capabilities on previously seen knowledge remains a challenge. |
| Approach: | They propose a synthetic knowledge ingestion method that leverages fine-grained synthesis and interleaved generation to construct high-quality data representations from raw knowledge sources. |
| Outcome: | The proposed method outperforms baseline methods on question-answering tasks spanning finance, biomedicine, and open-generation domains. |
Disentangling Continued Pre-Training: Attention-Driven Routing and Semantic Hub Preservation in Language Adaptation (2026.findings-acl)
Copied to clipboard
| Challenge: | Continued Pre-Training (CPT) enables Large Language Models (LLMs) to acquire second-language capabilities, yet the mechanisms underlying CPT remain poorly understood. |
| Approach: | They investigate how CPT adapts model representations across diverse language families and scripts, model sizes, and architectures. |
| Outcome: | The proposed model can be surgically transferred between base and CPT models with minimal loss. |
A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM𝛥 Integration into Upcycled MoE (2026.acl-long)
Copied to clipboard
Hao Zhou, Tianhao Li, Zhijun Wang, Shuaijie She, Linjuan Wu, Hao-Ran Wei, Baosong Yang, Jiajun Chen, Shujian Huang
| Challenge: | Large Language Models (LLMs) are expensive and require extensive Continued Pre-Training and data-intensive alignment to expand. |
| Approach: | They propose a method which upcycles a dense model into a Mixture-of-Experts architecture, allocating different experts to different languages. |
| Outcome: | Experiments show that the proposed model upcycles a dense model into a Mixture-of-Experts(MoE) architecture, allocating different experts to different languages. |
Memorization vs. Reasoning: Updating LLMs with New Knowledge (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods and benchmarks focus on entity substitutions, failing to capture the full breadth of complex real-world dynamics. |
| Approach: | They propose an automatic pipeline for simulating realistic knowledge updates reflected in an evidence corpus. |
| Outcome: | The proposed method outperforms prior continued pre-training (CPT) baselines on two LLM families and improves direct probing (memorization) results by 25.4%. |
Emergent Abilities of Large Language Models under Continued Pre-training for Language Adaptation (2025.acl-long)
Copied to clipboard
| Challenge: | Existing large language models are notoriously English-centric, and their performance has been reported to drop significantly in lessresourced languages. |
| Approach: | They propose a language-agnostic benchmark for in-context learning that reveals catastrophic forgetting early on CPT when English is not included. |
| Outcome: | The proposed method does not impact validation perplexity but is critical for emergence of downstream capabilities in the target language. |
CSRP: Chain-of-Thought Reasoning for Chinese Text Correction via Reinforcement Learning with Efficiency-Aware Rewards (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models lack specialized priors for subtle grammatical distinctions, and Supervised Fine-Tuning fails to optimize for precision-focused metrics. |
| Approach: | They propose a framework that builds correction capability through Continual Pre-training on 5.9M balanced samples to internalize domain knowledge. |
| Outcome: | The proposed framework outperforms existing models on the NACGEC benchmark with 50.99 F0.5 and 57.17 precision while mitigating over-correction bias. |
SciPedia: Unlocking the Value of Scientific Data for Pre-training (2026.acl-long)
Copied to clipboard
| Challenge: | High-quality scientific data is critical for advancing LLMs, yet academic literature remains underutilized. |
| Approach: | They construct a large-scale raw scientific corpus but identify a critical Learnability Gap . they develop a multi-stage pipeline featuring content cleaning and pedagogical augmentation . |
| Outcome: | The proposed approach boosts average performance by +2.12 (3B) and +2.95 (7B) on in-domain tasks. |