Papers with stage training strategy
Towards Making the Most of Cross-Lingual Transfer for Zero-Shot Neural Machine Translation (2022.acl-long)
Copied to clipboard
| Challenge: | Existing unsupervised neural machine translation systems can degrade when labeled data is limited. |
| Approach: | They propose a multilingual pretraining and multilingual fine-tuning for facilitating cross-lingual transfer in zero-shot translation using a parallel dataset. |
| Outcome: | The proposed model outperforms state-of-the-art models on many-to-English translation by over 7.2 and 5.0 BLEU. |
CULG: Commercial Universal Language Generation (2022.naacl-industry)
Copied to clipboard
| Challenge: | Pre-trained language models have improved performance for many NLP tasks in finance and healthcare. |
| Approach: | They propose a large-scale commercial universal language generation model which is pre-trained on a corpus drawn from 10 markets across 7 languages. |
| Outcome: | The proposed model outperforms other models on commercial generation tasks and on other markets, languages, and tasks. |
Fusing Highly Specialized Language Models for Comprehensive Expertise (2025.acl-long)
Copied to clipboard
Ning Ding, Yulin Chen, Ganqu Cui, Xingtai Lv, Weilin Zhao, Kaiyan Zhang, Ruobing Xie, Bowen Zhou, Zhiyuan Liu, Maosong Sun
| Challenge: | Existing models that focus on language, programming code, and mathematical symbols are not able to achieve mastery of all three domains simultaneously. |
| Approach: | They propose to fuse highly-specialized models that are already sufficiently trained on different domains to achieve a highly-specific model. |
| Outcome: | The proposed model could achieve mastery of the three crucial domains simultaneously. |
Complicate Then Simplify: A Novel Way to Explore Pre-trained Models for Text Classification (2022.coling-1)
Copied to clipboard
| Challenge: | Existing frameworks for text classification employing pre-trained models are constrained by the difficulty of the task. |
| Approach: | They propose a framework which implements a two-stage training strategy to fully exploit the knowledge in pre-trained models. |
| Outcome: | The proposed framework outperforms state-of-the-art classification models on six text classification corpora. |
Fin-ExBERT: User Intent based Text Extraction in Financial Context using Graph-Augmented BERT and trainable Plugin (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Financial dialogue transcripts pose a unique challenge for sentence-level information extraction due to their informal structure, domain-specific vocabulary, and variable intent density. |
| Approach: | They propose a framework for extracting user intent–relevant sentences from financial service calls. |
| Outcome: | The proposed framework shows strong precision and F1 performance on real-world transcripts . financial transcripts are a challenge due to their informal structure and domain-specific vocabulary . |
Learn To Remember: Transformer with Recurrent Memory for Document-Level Machine Translation (2022.findings-naacl)
Copied to clipboard
| Challenge: | Recent studies have shown that the effective use of contextual information between sentences can achieve better performance in document-level machine translation. |
| Approach: | They propose a recurrent memory unit to the Transformer to support the information exchange between the sentence and previous context. |
| Outcome: | The proposed model outperforms the previous work on TED and News by 0.91 s-BLEU and 1.49 d-BLUE on average. |
Towards Better Utilization of Multi-Reference Training Data for Chinese Grammatical Error Correction (2024.findings-acl)
Copied to clipboard
| Challenge: | a high proportion of Chinese training data is multi-referenced for the grammatical error correction task . however, there are many ways to correct an erroneous input sentence . a systematic study on multi-referencing training data has been proposed . |
| Approach: | They propose two new approaches and a simple two-stage training strategy to better utilize multi-reference training data. |
| Outcome: | The proposed methods show that Chinese training data contain multiple references. |
Omni-Chart-600K: A Comprehensive Dataset of Chart Types for Chart Understanding (2025.findings-naacl)
Copied to clipboard
Shulei Wang, Shuai Yang, Wang Lin, Zirun Guo, Sihang Cai, Hai Huang, Ye Wang, Jingyuan Chen, Tao Jin
| Challenge: | Existing chart-related training methods lack capabilities in information extraction, mathematical reasoning, and understanding of multiple chart types. |
| Approach: | They propose a two-stage training strategy and method for jointly training a vision encoder tailored for multi-type charts to address the deficiencies in chart types and limited scope of chart tasks in existing datasets. |
| Outcome: | The proposed dataset includes 21 diverse chart types and tasks, including data retrieval and mathematical reasoning. |
VIMI: Grounding Video Generation through Multi-modal Instruction (2024.emnlp-main)
Copied to clipboard
Yuwei Fang, Willi Menapace, Aliaksandr Siarohin, Tsai-Shien Chen, Kuan-Chieh Wang, Ivan Skorokhodov, Graham Neubig, Sergey Tulyakov
| Challenge: | Existing text-to-video diffusion models rely on text-only encoders for their pretraining, restricting their versatility and application in multimodal integration. |
| Approach: | They propose a multimodal conditional video generation framework for pretraining on augmented text prompts and then utilize a two-stage training strategy to enable diverse video generation tasks within a model. |
| Outcome: | The proposed model can synthesize consistent and temporally coherent videos with large motion while retaining the semantic control. |
MuMath-Code: Combining Tool-Use Large Language Models with Multi-perspective Data Augmentation for Mathematical Reasoning (2024.emnlp-main)
Copied to clipboard
| Challenge: | a method to combine the advantages of open-source and tool-free LLMs remains to be explored. |
| Approach: | They propose a method to integrate open-source LLMs with external Python interpreters and augment math reasoning data. |
| Outcome: | The proposed method improves on GSM8K and MATH with the use of external tools. |
UNIMO-G: Unified Image Generation through Multimodal Conditional Diffusion (2024.acl-long)
Copied to clipboard
| Challenge: | Existing text-to-image diffusion models generate images from text prompts due to inherent brevity of textual descriptions . however, the ability to accurately synthesize images with intricate details, such as specific entities or scenes, is limited due to the inherent bribery of text descriptions. |
| Approach: | They propose a multimodal conditional diffusion framework that operates on multimodal prompts with interleaved textual and visual inputs. |
| Outcome: | The proposed framework excels in both text-to-image generation and zero-shot subject-driven synthesis. |
AdaCQR: Enhancing Query Reformulation for Conversational Search via Sparse and Dense Retrieval Alignment (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods to address conversational search challenges are limited by one specific retrieval system. |
| Approach: | They propose a framework to enhance generalizability of information-seeking queries by aligning reformulation models with term-based and semantic retrieval systems. |
| Outcome: | The proposed framework outperforms existing methods in a more efficient framework. |
PRISM: Probabilistic Reward Model with Inherent Structural Modeling (2026.acl-long)
Copied to clipboard
| Challenge: | Existing evaluators compress diverse human judgments into a single scalar, leading to brittle alignment and reward hacking. |
| Approach: | They propose a Gaussian-based reinterpretation of reward evaluation as a conditional distribution and a mixture of Gaussians to capture conflicting preference dimensions. |
| Outcome: | The proposed model outperforms scalar baselines in accuracy and generalization. |
Knowledge Decoupling via Orthogonal Projection for Lifelong Editing of Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for enhancing large language models (LLMs) have achieved some success, but their knowledge understanding and memory capacity significantly degrades after extensive editing. |
| Approach: | They propose a method that stores the basis vectors of the representation space of past edits in a knowledge cache and projects the gradient of the current edit onto a space orthogonal to previous knowledge for updating. |
| Outcome: | The proposed method improves question-answering ability and hallucination mitigation by 14% and 61% for large language models after 3,000 edits. |
Warm Up Before You Train: Unlocking General Reasoning in Resource-Constrained Settings (2025.emnlp-main)
Copied to clipboard
| Challenge: | Reasoning-capable large language models (LLMs) have driven a major shift in artificial intelligence . these models generate long CoTs, capturing reasoning behaviors such as self-reflection, self-correction, and hypothesis testing. |
| Approach: | They propose a sample-efficient, two-stage training strategy to build reasoning LLMs . they "warm up" a model by distilling Long CoTs from a toy domain to acquire general reasoning skills . |
| Outcome: | The proposed training strategy outperforms existing models on a range of tasks. |
Smart-Searcher: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning (2025.findings-emnlp)
Copied to clipboard
Huatong Song, Jinhao Jiang, Wenqing Tian, Zhipeng Chen, Yuhuan Wu, Jiahao Zhao, Yingqian Min, Xin Zhao, Lei Fang, Ji-Rong Wen
| Challenge: | Large Language Models (LLMs) are powerful but prone to hallucinations due to static knowledge. Retrieval-augmented generation (RAG) helps by injecting external information, but current methods are costly, generalize poorly, or ignore the model’s internal knowledge. |
| Approach: | They propose a framework to train large language models to leverage both internal and external knowledge sources. |
| Outcome: | The proposed framework outperforms existing methods and achieves efficient retrieval-augmented reasoning. |
Benchmarking and Enabling Efficient Chinese Medical Retrieval via Asymmetric Encoders (2026.acl-long)
Copied to clipboard
| Challenge: | Effective medical text retrieval requires high accuracy and low latency. |
| Approach: | They propose a benchmark for medical text retrieval in Chinese using a symmetric architecture . CARE is a lightweight encoder with an LLM-based encoder for offline document encoding . |
| Outcome: | The proposed benchmark surpasses state-of-the-art symmetric models on CMedTEB . it matches high retrieval quality without increasing latency, and it performs well on a single GPU . |
Retrieving to Recover: Towards Incomplete Audio-Visual Question Answering via Semantic-consistent Purification (2026.acl-long)
Copied to clipboard
| Challenge: | Recent audio-visual question answering methods lack effective mechanisms for handling missing modalities, leading to performance degradation in real-world scenarios with data interruptions. |
| Approach: | They propose a framework that shifts the paradigm of missing modality handling to retrieval-based recovery . they leverage cross-modal retrieval via unified semantic embeddings to acquire missing domain-specific knowledge. |
| Outcome: | The proposed framework improves AVQA and enhances robustness in modal-incomplete scenarios. |
Reasoning-Aware AIGC Detection via Alignment and Reinforcement (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to AIGC detection have relied on statistical classifiers or black-box neural models, which exploit surface-level patterns and struggle to generalize as LLMs evolve. |
| Approach: | They propose a framework that generates interpretable reasoning chains before classification using supervised fine-tuning and reinforcement learning to improve accuracy. |
| Outcome: | The proposed framework achieves state-of-the-art performance across multiple benchmarks, offering a robust and transparent solution for AIGC detection. |
Retrieval-Augmented Fine-Tuning With Preference Optimization For Visual Program Generation (2025.acl-long)
Copied to clipboard
| Challenge: | Visual programming languages (VPLs) allow users to create programs through graphical interfaces, which results in easier accessibility and widespread usage in various domains. |
| Approach: | They propose to train VPLs from user instructions using large language models . they propose to use retrieval-augmented fine-tuning to leverage repetitive use of subroutines . |
| Outcome: | The proposed method outperforms prompting-based methods for LD generation accuracy even with smaller backbone models. |
InquireMobile: Teaching VLM-based Mobile Agent to Request Human Assistance via Reinforcement Fine-Tuning (2026.acl-long)
Copied to clipboard
Qihang Ai, Pi Bu, Yue Cao, Yingyao Wang, Jihao Gu, Jingxuan Xing, Zekun Zhu, Wei Jiang, Zhicheng Zheng, Jun Song, Yuning Jiang
| Challenge: | Recent advances in Vision-Language Models (VLMs) have enabled mobile agents to perceive and interact with real-world mobile environments based on human instructions. |
| Approach: | They propose a vision-language model that actively seeks human confirmation at critical decision points and a model inspired by reinforcement learning. |
| Outcome: | The proposed model achieves an improvement of 46.8% in inquiry success rate and the best overall success rate among existing baselines on InquireBench. |