Papers with curriculum learning
Domain Adaptation with BERT-based Domain Classification and Data Selection (D19-61)
Copied to clipboard
| Challenge: | Modern deep neural models with millions of parameters can easily adapt to a new learning task and dataset when enough supervision is given. |
| Approach: | They propose a domain adaptation framework based on curriculum learning and domain-discriminative data selection. |
| Outcome: | The proposed framework outperforms discrepancy-based methods on transfer tasks while consuming only fraction of training budget. |
Predicting Difficulty and Discrimination of Natural Language Questions (2022.acl-short)
Copied to clipboard
| Challenge: | Item Response Theory (IRT) has been used to numerically characterize question difficulty and discrimination for human subjects in domains including cognitive psychology and education. |
| Approach: | They explore the relationship between difficulty and discrimination in question-answering contexts by using IRT to characterize item difficulty and item discrimination. |
| Outcome: | The proposed models can predict difficulty and discrimination parameters for new questions and explain them with features of questions, answers, and associated contexts. |
SLR: Automated Synthesis for Scalable Logical Reasoning (2026.acl-long)
Copied to clipboard
Lukas Helff, Ahmad Omar, Felix Friedrich, Antonia Wüst, Hikaru Shindo, Rupert Mitchell, Tim Woydt, Patrick Schramowski, Wolfgang Stammer, Kristian Kersting
| Challenge: | Existing benchmarks intended to evaluate reasoning capabilities emphasize deductive reasoning, where conclusions necessarily follow from given premises. |
| Approach: | They propose an end-to-end framework for systematic evaluation and training of Large Language Models via Scalable Logical Reasoning. |
| Outcome: | The proposed framework doubles Llama-3-8B accuracy on SLR-Bench, achieving parity with Gemini-Flash-Thinking at a fraction of computational cost. |
TAKE: Topic-shift Aware Knowledge sElection for Dialogue Generation (2022.coling-1)
Copied to clipboard
| Challenge: | Recent work finds that realizing who holds the initiative can help select knowledge . however, there is a strong semantic transition between two rounds, probably leading to initiative misjudgment . |
| Approach: | They propose a topic-shift Aware Knowledge sElector(TAKE) model which locates relevant parts from dialogue history to improve knowledge selection. |
| Outcome: | The proposed model outperforms baseline models on the WoW. |
Communication Enables Cooperation in LLM Agents: A Comparison with Curriculum-Based Approaches (2026.eacl-short)
Copied to clipboard
| Challenge: | a "cheap talk" channel increases cooperation in 4-player Stag Hunt, but a complex curriculum can induce "learned pessimism" in agents. |
| Approach: | They investigate whether a direct communication channel can elicit cooperation in multi-agent LLMs. |
| Outcome: | The proposed curriculum reduces agent payoffs by 27.4% in a 4-player Stag Hunt simulation. |
Progressive Self-Training with Discriminator for Aspect Term Extraction (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to extract aspect terms from review sentences are limited due to lack of annotated data. |
| Approach: | They propose to refine conventional self-training to progressive self-teaching to reduce noise . they use a discriminator to filter the noisy pseudo-labels. |
| Outcome: | The proposed model outperforms baseline models and achieves state-of-the-art performance on four SemEval datasets. |
Edit Distance Based Curriculum Learning for Paraphrase Generation (2021.acl-srw)
Copied to clipboard
| Challenge: | Existing studies show that curriculum learning improves translation quality on machine translation . paraphrase generation allows a certain level of semantic divergence between source and target . |
| Approach: | They propose to apply curriculum learning to paraphrase generation for the first time . they propose to use edit distance to improve paraphrase quality . |
| Outcome: | The proposed method improves paraphrase generation quality, compared with previous methods . it uses edit distance, which is not possible for previous methods, the authors say . |
Training Language Models under Resource Constraints for Adversarial Advertisement Detection (2021.naacl-industry)
Copied to clipboard
| Challenge: | e-commerce and social media sites require content moderation to ensure ethical standards . a tiered moderation workflow with automated components complements human experts . |
| Approach: | They propose techniques for training text classification models under resource constraints . they use weak supervision, curriculum learning and multi-lingual training to fine-tune BERT . |
| Outcome: | The proposed techniques detect adversarial ads with a substantial gain over baseline . the authors show that the proposed methods can be applied to multiple languages . |
Knowledge Graph Entity Typing with Curriculum Contrastive Learning (2025.coling-main)
Copied to clipboard
| Challenge: | Existing knowledge graphs suffer from incomplete type annotations because they are manually constructed by domain experts. |
| Approach: | They propose a CCLET model using the Curriculum Contrastive Learning strategy for KGET to fuse the entity related semantic and the structural information of the Knowledge Graph (KG) they define the difficulty of the course by controlling the level of added noise and aim to accurately learn with curriculum contrastive learning strategy from easy to difficult. |
| Outcome: | The proposed model outperforms state-of-the-art models and is highly accurate across multiple learning environments. |
Curriculum Learning for Small Code Language Models (2024.acl-srw)
Copied to clipboard
| Challenge: | Existing studies have shown that curriculum learning improves performance of code language models when it comes to complex tasks. |
| Approach: | They propose a novel code difficulty assessment metric and introduce a Novel Curriculum Learning schedule that enhances the performance of small decoder-only language models. |
| Outcome: | The proposed model improves on code execution tasks while its effect on code completion is less significant. |
CDL: Curriculum Dual Learning for Emotion-Controllable Response Generation (2020.acl-main)
Copied to clipboard
| Challenge: | Existing methods for generating emotion-controllable response are inadequate due to content consistency and lack of coherence. |
| Approach: | They propose a framework that extends the emotion-controllable response generation to a dual task to generate emotional responses and emotional queries alternatively. |
| Outcome: | The proposed framework outperforms baseline models in coherence, diversity, and relation to emotion factors. |
A Versatile Adaptive Curriculum Learning Framework for Task-oriented Dialogue Policy Learning (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing training paradigms for dialogue policy learning with brute-force random sampling are expensive and lack reliable evaluation of difficulty scores. |
| Approach: | They propose a flexible adaptive curriculum learning framework that integrates curriculum learning with a generic global curriculum. |
| Outcome: | The proposed framework improves learning performance and efficiency on three public dialogue datasets. |
Reflect-RL: Two-Player Online RL Fine-Tuning for LMs (2024.acl-long)
Copied to clipboard
| Challenge: | supervised fine-tuning (SFT) on a limited offline dataset does not yield good performance. |
| Approach: | They propose a two-player system to fine-tune an LM using SFT and online RL . they use negative example generation to enhance error-correction ability of the reflection model . |
| Outcome: | The proposed system outperforms SFT and online RL without reflection on a GPT-2 XL 1.56B model. |
Does the Order of Training Samples Matter? Improving Neural Data-to-Text Generation with Curriculum Learning (2021.eacl-main)
Copied to clipboard
| Challenge: | Recent advances in data-to-text generation have been focused on curriculum learning, which is a process of presenting training data in a specific order, starting from easy examples and moving on to more difficult ones, as the learner becomes more competent. |
| Approach: | They propose to use a curriculum learning process to change the order of training samples in a model based on the model's competence to improve model performance and convergence speed. |
| Outcome: | The proposed model shows faster convergence speed and reduced training time by 38.7% and performance by 4.84 BLEU. |
From Sentences to Proof Trees: Leveraging Language Models for Structured Reasoning (2026.eacl-srw)
Copied to clipboard
| Challenge: | Multi-hop reasoning requires a chain of facts to reflect the reasoning behind the answer. |
| Approach: | They propose an inference-guided prompting approach that performs well in natural language questions . they propose a neuro-symbolic approach to reasoning using large language models . |
| Outcome: | The proposed model outperforms all prompting strategies and fine-tunes LLMs trained specifically for proof generation. |
On Curriculum Learning for Commonsense Reasoning (2022.naacl-main)
Copied to clipboard
| Challenge: | Recent research suggests that data order can have a significant impact on the performance of finetuned models for natural language understanding. |
| Approach: | They use paced curriculum learning to rank data and sample training mini-batches with increasing levels of difficulty during finetuning. |
| Outcome: | The proposed model improves performance for socialIQA, CosmosQA, CODAH, HellaSwag, WinoGrande in both tuning settings. |
Dialo-AP: A Dependency Parsing Based Argument Parser for Dialogues (2022.coling-1)
Copied to clipboard
| Challenge: | a recent work on argument mining has focused on parsing monologues, while neglecting dialogues. |
| Approach: | They propose an end-to-end argument parser that constructs argument graphs from dialogues . they use extensive pre-training and curriculum learning to train AM . |
| Outcome: | The proposed system performs all sub-tasks of AM and achieves significant improvements . it is compared to existing systems and validated through human evaluation . |
Self-Paced Learning for Neural Machine Translation (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies have shown that the training of neural machine translation (NMT) rely on the quality of artificial schedule drawn up with the handcrafted features, e.g. sentence length or word rarity. |
| Approach: | They propose to train NMT model using a self-paced learning approach that allows it to quantify the learning confidence over training examples and flexibly govern its learning via regulating the loss in each iteration step. |
| Outcome: | The proposed model outperforms baseline models and those trained with human-designed curricula on translation quality and convergence speed. |
Extracting Symptoms and their Status from Clinical Conversations (P19-1)
Copied to clipboard
| Challenge: | Existing models for extracting symptoms from clinical conversations are inherently difficult. |
| Approach: | They propose two new deep learning models tailored for a new application . they propose a hierarchical span-attribute tagging model and a sequence-to-sequence model . |
| Outcome: | The proposed models perform well under different conditions and are compared to existing models. |
FinRAG-12B: A Production-Validated Recipe for Grounded Question Answering in Banking (2026.acl-industry)
Copied to clipboard
| Challenge: | Large language models (LLMs) are rapidly being adopted across various domains, but adoption in the regulated banking industry is limited due to their tendency to hallucinate, exhibit over-agreeable behavior, and lack alignment with domain-specific knowledge and constraints. |
| Approach: | They propose a framework for training grounded domain-specific LLMs that optimizes answer quality, citation grounding, and calibrated refusal under real-world deployment constraints. |
| Outcome: | The proposed model outperforms GPT-4.1 on citation grounding and calibrated refusal under real-world deployment constraints. |
Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialogue State Tracking (2021.acl-short)
Copied to clipboard
| Challenge: | Existing dialog state tracking models neglect rich structural information in a dataset. |
| Approach: | They propose to use curriculum learning to leverage dialog state tracking data . they propose a model-agnostic framework that pre-trains a DST model with schema information . |
| Outcome: | The proposed framework improves performance over a transformer-based and RNN-based model on WOZ2.0 and MultiWOZ2.1. |
Combining Curriculum Learning and Knowledge Distillation for Dialogue Generation (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies have shown that curriculum learning facilitates dialogue generation tasks while knowledge distillation can yield significant performance boosts for student models. |
| Approach: | They propose a combination of curriculum learning and knowledge distillation for dialogue generation models . they cluster training cases according to their complexity and employ an adversarial training strategy . |
| Outcome: | The proposed model improves compared with baselines. |
MathMixup: Boosting LLM Mathematical Reasoning with Difficulty-Controllable Data Synthesis and Curriculum Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing data synthesis methods suffer from limited diversity and lack precise control over problem difficulty, making them insufficient for efficient training paradigms such as curriculum learning. |
| Approach: | They propose a data synthesis paradigm that generates high-quality, difficulty-controllable mathematical reasoning problems through hybrid and decomposed strategies. |
| Outcome: | The proposed paradigm outperforms existing methods and improves mathematical reasoning abilities. |
Quantifying Appropriateness of Summarization Data for Curriculum Learning (2021.eacl-main)
Copied to clipboard
| Challenge: | Summarization datasets are noisy, and summaries often do not reflect what is written in the source texts. |
| Approach: | They propose a method of curriculum learning to train summarization models from noisy data. |
| Outcome: | The proposed method improves the performance of pretrained and non-pretrained models on human evaluation. |
Efficient Contrastive Learning via Novel Data Augmentation and Curriculum Learning (2021.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies describe how to apply contrastive learning to the language domain but it is difficult to apply data augmentation methods directly to language modeling. |
| Approach: | They propose a memory-efficient continual pretraining method that applies contrastive learning with novel data augmentation and curriculum learning. |
| Outcome: | The proposed method outperforms baseline models on sentence-level tasks with only 70% of memory compared to the baseline model. |
Complexity-Guided Curriculum Learning for Text Graphs (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Curriculum learning is a systematic approach to training that refines training progressively and tailors training to task requirements. |
| Approach: | They propose a curriculum learning approach that employs "spaced repetition" and complexity formalisms to guide the training process. |
| Outcome: | The proposed model gains more and uses less data, and the best curricula are equally effective. |
Mitigating Data Scarceness through Data Synthesis, Augmentation and Curriculum for Abstractive Summarization (2021.findings-emnlp)
Copied to clipboard
| Challenge: | a new study explores data manipulation techniques for improving abstractive summarization models without the need for any additional data. |
| Approach: | They propose a method of data synthesis with paraphrasing, data augmentation with sample mixing and curriculum learning with new difficulty metrics based on specificity and abstractiveness. |
| Outcome: | The proposed techniques improve abstractive summarization models without additional data . the proposed techniques can be applied in isolation and when combined . |
Generative Entity Typing with Curriculum Learning (2022.emnlp-main)
Copied to clipboard
| Challenge: | Entity typing fails to assign an entity to the types beyond the predefined type set. |
| Approach: | They propose a generative entity typing paradigm that assigns types to entities . traditional classification-based approaches fail to assign entities to the types beyond the predefined set . they employ curriculum learning to train the model on heterogeneous data . |
| Outcome: | The proposed model outperforms the state-of-the-art model on heterogeneous training data. |
Entropy Scheduling in Reinforcement Learning for Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | entropy in reinforcement learning functions analogously to the learning rate in LLMs. |
| Approach: | They propose an entropy scheduling system that optimizes different pre-set goals by controlling and scheduling entropicy at each step of the RL process. |
| Outcome: | The proposed method improves AIME2024 from 50.9 to 54.9 within 40 training steps. |
Curriculum Learning Meets Weakly Supervised Multimodal Correlation Learning (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies have used the correlation information stored in samples for self-supervised learning, but they feed the training pairs in a random order without consideration of difficulty. |
| Approach: | They propose to inject curriculum learning into weakly supervised multimodal correlation learning by scoring and feeding pairs according to difficulty. |
| Outcome: | The proposed model achieves state-of-the-art on multimodal sentiment analysis without human annotation. |
SKIntern: Internalizing Symbolic Knowledge for Distilling Better CoT Capabilities into Small Language Models (2025.coling-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have high computational costs and privacy concerns due to their high computational expenses and data privacy. |
| Approach: | They propose a method that empowers SLMs to internalize symbolic knowledge and few-shot examples gradually through a progressive fine-tuning process. |
| Outcome: | The proposed approach outperforms state-of-the-art baselines by over 5% while reducing inference costs by up to 4 across a wide range of SLMs in both in-domain (ID) and out-of domain (OOD) tasks. |
Adaptive Gating in Mixture-of-Experts based Language Models (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing models employ a fixed gating network where each token is computed by the same number of experts. |
| Approach: | They propose a flexible training strategy that allows tokens to be processed by a variable number of experts based on expert probability distribution. |
| Outcome: | The proposed model reduces training time and inference quality while maintaining sparsity while maintaining inference accuracy. |
PLATO-2: Towards Building an Open-Domain Chatbot via Curriculum Learning (2021.findings-acl)
Copied to clipboard
| Challenge: | PLATO-2 is a high-quality open-domain chatbot that can generate one-to-many mappings and improve response quality. |
| Approach: | They propose a curriculum learning process to build a high-quality open-domain chatbot . they use a coarse-grained generation model and latent variables to train a generative model . |
| Outcome: | The proposed model improves on Chinese and English data and can generate diverse responses and select the best response. |
Distilling Causal Effect from Miscellaneous Other-Class for Continual Named Entity Recognition (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for Named Entity Recognition (NER) are not able to learn Other-Class in the same way as new entity types. |
| Approach: | They propose a unified causal framework to retrieve causality from new entity types and Other-Class. |
| Outcome: | The proposed method outperforms the state-of-the-art method on three benchmark datasets. |
RoChBert: Towards Robust BERT Fine-tuning for Chinese (2022.findings-emnlp)
Copied to clipboard
Zihan Zhang, Jinfeng Li, Ning Shi, Bo Yuan, Xiangyu Liu, Rong Zhang, Hui Xue, Donghong Sun, Chao Zhang
| Challenge: | Pre-trained language models (e.g., BERT) have been proved vulnerable to adversarial texts. |
| Approach: | They propose to fuse Chinese phonetic and glyph features into pre-trained models by using a more comprehensive adversarial graph. |
| Outcome: | The proposed framework outperforms existing methods in significant ways on a wide range of tasks while remaining accurate on benign texts. |
Bootstrapped Policy Learning for Task-oriented Dialogue through Goal Shaping (2024.emnlp-main)
Copied to clipboard
| Challenge: | Despite the promise of reinforcement learning, achieving seamless knowledge transitions in complex dialogue environments is difficult. |
| Approach: | They propose a Bootstrapped Policy Learning framework which adaptively tailors progressively challenging subgoal curriculum for each complex goal through goal shaping. |
| Outcome: | The proposed framework has shown to be effective across four publicly available datasets with different difficulty levels. |
Beyond Random Sampling: Efficient Language Model Pretraining via Curriculum Learning (2026.eacl-long)
Copied to clipboard
| Challenge: | Curriculum learning has improved efficiency across machine learning domains, but remains underexplored for language model pretraining. |
| Approach: | They present a systematic investigation of curriculum learning in LLM pretraining . they use vanilla curriculum learning, pacing-based sampling, and interleaved curricula . |
| Outcome: | The proposed framework accelerates convergence in early and mid-training phases, reducing training steps by 18-45% to reach baseline performance. |
Tackling Distractor Documents in Multi-Hop QA with Reinforcement and Curriculum Learning (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing work on retrieval-augmented generation systems has shown that retrievers exhibit imperfect recall and precision, limiting downstream performance. |
| Approach: | They propose a retrieval-augmented generation model that generates answers from larger sets of retrieved contexts. |
| Outcome: | The proposed model generates answers and cites relevant information from larger sets of retrieved contexts. |
CLFFRD: Curriculum Learning and Fine-grained Fusion for Multimodal Rumor Detection (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing multimodal rumor detection models overlook sample difficulty and order when training . Existing models overlook text-level difficulty, image-level and multimodal difficulty when training samples . |
| Approach: | They propose a curriculum learning framework that uses fine-grained fusion to detect rumors . they propose fusion-based methods that combine text and images to enhance semantic cohesion . |
| Outcome: | The proposed framework outperforms state-of-the-art models on English and Chinese benchmark datasets. |
Code Execution with Pre-trained Language Models (2023.findings-acl)
Copied to clipboard
Chenxiao Liu, Shuai Lu, Weizhu Chen, Daxin Jiang, Alexey Svyatkovskiy, Shengyu Fu, Neel Sundaresan, Nan Duan
| Challenge: | Pre-trained code intelligence models ignore the execution trace and only rely on source code and syntactic structures to understand code execution. |
| Approach: | They develop a mutation-based data augmentation technique to create a Python dataset and task for code execution that challenges existing models. |
| Outcome: | The proposed model outperforms existing models on code execution and shows its potential for zero-shot code-to-code search and text-to code generation. |
Calibrated Progressive Distillation: Co-Designing Curriculum and Target Mixing for Knowledge Distillation of Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for knowledge distillation address the teacher–student capacity gap by mixing teacher and student distributions in the distillation target or using curriculum learning to sequence training from easy to hard examples. |
| Approach: | They propose a white-box KD framework that co-designs curriculum scheduling and target mixing through a unified difficulty-aware principle. |
| Outcome: | The proposed framework outperforms existing methods while reducing training runtime by over 10%. |
Supervised Prototypical Contrastive Learning for Emotion Recognition in Conversation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to capture emotions in conversation (ERC) lack the correlation between emotions and semantics, resulting in many challenges. |
| Approach: | They propose a Supervised Prototypical Contrastive Learning (SPCL) loss for the ERC task . they use a Prototype Network to leverage the supervised contrastive learning approach . |
| Outcome: | The proposed approach outperforms CoG-BART's proposed approach on three widely used benchmarks and shows that it is effective on multiple scenarios. |
Curriculum Learning for Graph Neural Networks: A Multiview Competence-based Approach (2023.acl-long)
Copied to clipboard
| Challenge: | Existing curriculum learning approaches often employ a single criterion of difficulty in their training paradigms. |
| Approach: | They propose a new approach that builds on graph complexity formalisms and model competence during training. |
| Outcome: | The proposed approach improves learning efficiency on real-world link prediction and node classification tasks. |
Balancing Knowledge Breadth and Task Depth for Effective Domain Adaptation Fine-Tuning (2026.findings-acl)
Copied to clipboard
| Challenge: | a lack of knowledge breadth and task depth can hinder curriculum learning in domains such as medicine and finance. |
| Approach: | They propose a two-dimensional curriculum learning framework that coordinates model training along two orthogonal axes: the knowledge dimension and the task dimension. |
| Outcome: | The proposed framework improves accuracy on medical evaluations by 2.49% and on financial evaluations 1.2% compared with the second-best method. |
Code-Switching Curriculum Learning for Multilingual Transfer in LLMs (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) exhibit near human-level performance in various tasks, but performance drops after a handful of high-resource languages due to the imbalance in pre-training data. |
| Approach: | They propose a code-switching curriculum learning model to enhance cross-lingual transfer for LLMs by progressively training models with a curriculum consisting of token-level code-changing, sentence-level codeswitching, and monolingual corpora. |
| Outcome: | The proposed model improves language transfer to Korean, with significant gains in Japanese and Indonesian . the proposed model mitigates spurious correlations between language resources and safety alignment . |
Few-Shot Text Classification with Triplet Networks, Data Augmentation, and Curriculum Learning (2021.naacl-main)
Copied to clipboard
| Challenge: | a few-shot text classification task requires a large number of output classes, with few training examples per class. |
| Approach: | They propose a data augmentation technique suitable for training with limited data for few-shot, highly-multiclass text classification scenarios. |
| Outcome: | The proposed technique improves performance on four classification tasks by 3.0% on average. |
Problem-Solving Logic Guided Curriculum In-Context Learning for LLMs Complex Reasoning (2025.findings-acl)
Copied to clipboard
| Challenge: | In-context learning (ICL) can enhance the complex reasoning capabilities of large language models. |
| Approach: | They propose a curriculum ICL strategy guided by problem-solving logic to select demonstration examples based on curriculum learning. |
| Outcome: | The proposed strategy outperforms existing methods on multiple benchmarks. |
Staged Knowledge Distillation Through Least-to-Most Prompting: Optimizing Teacher Guidance via Difficulty-Aware Training (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Knowledge distillation (KD) enables the compression of large language models (LLMs) conventional methods suffer from training-inference mismatches and suboptimal performance due to expensive student-generated outputs. |
| Approach: | They propose a method that combines a CL strategy and adaptive loss design to reduce training mismatches and suboptimal performance. |
| Outcome: | L2M-KD outperforms existing white-box KD methods on instruction-following tasks . it outperformed existing methods, achieving superior student model performance with reduced overhead . |
Improving Both Domain Robustness and Domain Adaptability in Machine Translation (2022.coling-1)
Copied to clipboard
| Challenge: | Existing approaches to domain adaptation for NMT depend on high-quality parallel data. |
| Approach: | They propose a meta-learning framework which improves domain robustness and adaptability . they use a word-level domain mixing model and a domain classifier to integrate it . |
| Outcome: | The proposed approach improves domain robustness and adaptability in seen and unseen domains. |
Global Context-enhanced Graph Convolutional Networks for Document-level Relation Extraction (2020.coling-main)
Copied to clipboard
| Challenge: | Existing approaches to document-level relation extraction are difficult to establish direct connections between distant entity pairs. |
| Approach: | They propose a global context-enhanced Graph Convolutional Network model which captures rich global context information of entities in a document. |
| Outcome: | The proposed model captures rich global context information of entities in a document. |
LaSQuE: Improved Zero-Shot Classification from Explanations Through Quantifier Modeling and Curriculum Learning (2023.findings-acl)
Copied to clipboard
| Challenge: | Several recent approaches have explored training machine learning models via natural language supervision, but they fail to leverage linguistic quantifiers and mimic humans in compositionally learning complex tasks. |
| Approach: | They propose a method that can learn zero-shot classifiers from language explanations by using three new strategies: (1) modeling the semantics of linguistic quantifiers in explanations; (2) aggregating information from multiple explanations using an attention-based mechanism; (3) model training via curriculum learning. |
| Outcome: | The proposed method outperforms previous work showing an absolute gain of up to 7% in generalizing to unseen real-world classification tasks. |
Parsing Natural Language into Propositional and First-Order Logic with Dual Reinforcement Learning (2022.coling-1)
Copied to clipboard
Xuantao Lu, Jingping Liu, Zhouhong Gu, Hanwen Tong, Chenhao Xie, Junyang Huang, Yanghua Xiao, Wenguang Wang
| Challenge: | Existing methods to parse natural language into structured logical expressions have limitations due to paucity of labeled data. |
| Approach: | They propose a scoring model to automatically learn a model-based reward . they also propose introducing a Chinese-PL/FOL dataset to compensate for paucity of labeled data . |
| Outcome: | The proposed model outperforms competitors on several datasets. |
INREACT: An Inspire-Then-Reinforce Training Framework For Multimodal GUI Agent (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing multimodal large language models struggle with precise localization of small elements. |
| Approach: | They propose a multimodal GUI agent framework that unifies observing, thinking, and acting for precise and interpretable decision-making. |
| Outcome: | The proposed framework unifies observing, thinking, and acting for precise and interpretable decision-making. |
Simple and Effective Curriculum Pointer-Generator Networks for Reading Comprehension over Long Narratives (P19-1)
Copied to clipboard
Yi Tay, Shuohang Wang, Anh Tuan Luu, Jie Fu, Minh C. Phan, Xingdi Yuan, Jinfeng Rao, Siu Cheung Hui, Aston Zhang
| Challenge: | Using a pointer-generator framework for reading/sampling over large documents, we propose a framework for learning over long narratives where documents easily span over thousands of tokens. |
| Approach: | They propose a curriculum learning (CL) based pointer-generator framework for reading/sampling over large documents, enabling diverse training of the neural model based on the notion of alternating contextual difficulty. |
| Outcome: | The proposed framework improves on the NarrativeQA reading comprehension benchmark and reaches state-of-the-art performance. |
Language models can learn implicit multi-hop reasoning, but only if they have lots of training data (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies explore the ability of language models to solve multi-hop reasoning tasks without chain of thought. |
| Approach: | They propose to use GPT2-style language models to train k-hop reasoning models . they show that the required training data grows exponentially in k . |
| Outcome: | The proposed models can learn implicit reasoning without chain-of-thoughts, the authors show . their training data grows exponentially in k, and the required number of transformer layers grows linearly in the model. |
NDH-Full: Learning and Evaluating Navigational Agents on Full-Length Dialogue (2021.emnlp-main)
Copied to clipboard
| Challenge: | Vision-and-Dialogue Navigation is one of the tasks that evaluate the agent’s ability to interact with humans for assistance and navigate based on natural language responses. |
| Approach: | They propose a vision-and-dialogue navigation task which evaluates the agent's ability to interact with humans and navigate based on natural language responses. |
| Outcome: | The proposed model performs well on the Navigation from Dialogue History task, but it is not evaluated by the primary metric Goal Progress. |
Data Selection Curriculum for Abstractive Text Summarization (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Abstractive Text Summarization (ATS) models are commonly trained using large-scale data that is randomly shuffled. |
| Approach: | They propose a data selection curriculum scoring system that measures the learning difficulty of an ATS model and expected performance on an instance. |
| Outcome: | The proposed system surpasses baselines on CNN/DailyMail dataset, utilizing 20% of available instances. |
Uncertainty-Aware Curriculum Learning for Neural Machine Translation (2020.acl-main)
Copied to clipboard
| Challenge: | Neural machine translation (NMT) has proven to be facilitated by curriculum learning which presents examples in an easy-to-hard order at different training stages. |
| Approach: | They propose to use an uncertainty-aware curriculum learning approach to assess data difficulty and model competence to provide examples in an easy-to-hard order at different training stages. |
| Outcome: | The proposed approach outperforms baseline and related methods on translation quality and convergence speed. |
TheoremLlama: Transforming General-Purpose LLMs into Lean4 Experts (2024.emnlp-main)
Copied to clipboard
| Challenge: | a framework for formal proof writing using formal languages like Lean4 is needed to prove mathematical theorems using formal language. |
| Approach: | They propose a framework that trains a general-purpose LLM to be a Lean4 expert. |
| Outcome: | The proposed framework achieves cumulative accuracies of 36.48% and 33.61% on MiniF2F-Valid and Test datasets. |
Re-Examine Distantly Supervised NER: A New Benchmark and a Simple Approach (2025.coling-main)
Copied to clipboard
| Challenge: | Existing DS-NER approaches rely on large validation sets and test set for tuning inappropriately. |
| Approach: | They propose a method where training data is annotated using domain dictionaries and test data is analyzed by domain experts. |
| Outcome: | The proposed method reduces the need for labor-intensive manual annotations but rely on large human labeled validation set. |
CTC-based Non-autoregressive Speech Translation (2023.acl-long)
Copied to clipboard
Chen Xu, Xiaoqian Liu, Xiaowen Liu, Qingxuan Sun, Yuhao Zhang, Murun Yang, Qianqian Dong, Tom Ko, Mingxuan Wang, Tong Xiao, Anxiang Ma, Jingbo Zhu
| Challenge: | End-to-end speech translation (E2E ST) and non-autoregressive (NAR) generation are promising in language and speech processing for their advantages of less error propagation and low latency. |
| Approach: | They develop a model that uses connectionist temporal classification to predict the source and target texts. |
| Outcome: | The proposed model achieves an average BLEU score of 29.5 with a speed-up of 5.67. |
Mitigating Hallucinations in Large Vision-Language Models by Self-Injecting Hallucinations (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for hallucination mitigation are based on external dependency and require external annotations or auxiliary models for preference data collection. |
| Approach: | a new method is proposed to help model-generated hallucinations without external dependencies. |
| Outcome: | a new method that self-injects hallucinations into a generated response improves halluuutations mitigation. |
Enhancing Alignment using Curriculum Learning & Ranked Preferences (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Direct Preference Optimization (DPO) is an effective technique that leverages pairwise preference data to align LLMs to human preferences. |
| Approach: | They propose to use pairwise preference data to create multiple preference pairs for a given prompt. |
| Outcome: | The proposed method outperforms standard DPO on MTbench, Vicuna bench, and WizardLM with a score of 7.43 on the test sets. |
Let’s Be Self-generated via Step by Step: A Curriculum Learning Approach to Automated Reasoning with Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing efforts to improve CoT prompting have limitations that require extensive human effort or performance needs to be improved. |
| Approach: | They propose a prompt approach for automatic reasoning called LBS3 inspired by curriculum learning which better reflects human learning habits. |
| Outcome: | The proposed approach achieves strongly competitive performance compared to baselines in reasoning-intensive tasks with varying open- and closed-source LLMs. |
IT2ACL Learning Easy-to-Hard Instructions via 2-Phase Automated Curriculum Learning for Large Language Models (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing studies have focused on the pre-training phase of large language models, but this study focuses on the learning phase of pre-trained LLMs. |
| Approach: | They propose a 2-phase automated curriculum learning guided instruction tuning framework that learns easy-to-hard instructions in a self-adjusting dynamic manner. |
| Outcome: | The proposed framework unlocks latent ability in pre-trained large language models and achieving superior performance across diverse tasks. |
DynamicFocalPO: Adaptive Focusing Strategy for Preference Optimization (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent preference optimization algorithms such as Direct Preference Optimization (DPO) have become prevalent for aligning large language models with human preferences. |
| Approach: | They propose a preference optimization algorithm that introduces a modulating factor that down-weighs misranked preference pairs and employs focusing strategy that adapts over the course of training. |
| Outcome: | Experiments show that DynamicFocalPO surpasses both DPO and FocalPO on benchmarks including Alpaca Eval 2.0 and Arena-Hard using Mistral-Base-7B and Llama-3-Instruct-8B. |
CLewR: Curriculum Learning with Restarts for Machine Translation Preference Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated competitive performance in zero-shot multilingual machine translation (MT). |
| Approach: | They propose a curriculum learning strategy with restarts which reiterates easy-to-hard curriculum multiple times during training to effectively mitigate catastrophic forgetting of easy examples. |
| Outcome: | The proposed model replicates easy-to-hard curriculum multiple times during training to mitigate catastrophic forgetting of easy examples. |
PopALM: Popularity-Aligned Language Models for Social Media Trendy Response Prediction (2024.lrec-main)
Copied to clipboard
| Challenge: | Recent work focuses on generic human responses without considering popularity factors in the social contexts. |
| Approach: | They propose Popularity-Aligned Language Models to distinguish responses liked by a larger audience through reinforcement learning. |
| Outcome: | The proposed model can distinguish responses liked by a larger audience through reinforcement learning. |
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. |
NL2Lean: Translating Natural Language into Lean 4 through Multi-Aspect Reinforcement Learning (2025.emnlp-main)
Copied to clipboard
Yue Fang, Shaohan Huang, Xin Yu, Haizhen Huang, Zihan Zhang, Weiwei Deng, Furu Wei, Feng Sun, Qi Zhang, Zhi Jin
| Challenge: | Existing formal proof assistants rely on instruction tuning and lack fine-grained structural and semantic alignment. |
| Approach: | They propose a reinforcement learning framework that enables LLMs to translate natural language into formal language such as Lean 4 . they use a model with basic translation ability to refine the model's reinforcement learning . |
| Outcome: | The proposed method outperforms baseline models on NL-to-Lean 4 tasks. |
Progressive Re-ranking for Multimodal Retrieval-Augmented Generation via Curriculum Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to improve retrieval performance of large language models are limited by static knowledge. |
| Approach: | They propose a multimodal re-ranking framework that combines curriculum learning with fine-grained reranking and multimodal section reassessment to improve CLIP-based visual coarse-grain retrieval. |
| Outcome: | The proposed framework achieves state-of-the-art answer accuracy and competitive retrieval performance on InfoSeek and Enc-VQA. |
CodeRM-NT: Reward Model for Code RL without Unit Tests (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods rely on unit tests to evaluate code correctness and provide rewards, but these methods are difficult to verify at scale. |
| Approach: | They propose a code reward model that leverages Monte Carlo Tree Search guided by LLMs to generate code snippets and judges execution traces to annotate code with reward signals. |
| Outcome: | The proposed model outperforms synthetic unit tests on multiple code generation benchmarks and improves curriculum learning. |