Papers with two-stage approach
Learning from LLM Agents: In-Context Generative Models for Text Casing in E-Commerce Ads (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Existing NER-based transformer models are expensive and lack contextual dependencies, making them less reliable when handling unseen or ad-specific terms, e.g., brand names. |
| Approach: | They propose a two-stage approach to casing correction in e-commerce ad content that leverages Chain-of-Actions to enforce content policies while accurately handling ads-specific terms. |
| Outcome: | The proposed model outperforms existing NER-based models and achieves near-LLM performance at a fraction of the cost. |
Point Precisely: Towards Ensuring the Precision of Data in Generated Texts Using Delayed Copy Mechanism (C18-1)
Copied to clipboard
| Challenge: | Recent neural generation systems have shown significant progress on data-to-text generation tasks. |
| Approach: | They propose a two-stage approach with a delayed copy mechanism to improve the precision of data records in the generated texts. |
| Outcome: | The proposed approach improves the accuracy of the generated texts on a RotoWire dataset. |
Know the Unknown: An Uncertainty-Sensitive Method for LLM Instruction Tuning (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have impressive capabilities but face significant challenges from hallucinations, which arise from insufficient knowledge or context. |
| Approach: | They propose a novel two-stage approach for contextual question answering that enhances LLMs’ ability to recognise their knowledge boundaries while the second reinforces instruction adherence through carefully designed causal prompts. |
| Outcome: | The proposed approach significantly reduces incorrect answers in contextual QA and improves models’ faithfulness to parametric knowledge, mitigating hallucinations in general QA tasks. |
Building the Directed Semantic Graph for Coherent Long Text Generation (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for conditional long text generation ignore the coherence issue of the generated texts. |
| Approach: | They propose a two-stage approach to generate coherent long text based on short input text . they first build a document-level path for each output text with each sentence embedding as its node . |
| Outcome: | The proposed approach is superior to state-of-the-art approaches on three real-world datasets. |
SpanProto: A Two-stage Span-based Prototypical Network for Few-shot Named Entity Recognition (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for few-shot Named Entity Recognition ignore entity boundaries and are time-consuming . a seminal span-based prototypical network solves the problem using two stages: span extraction and mention classification. |
| Approach: | They propose a seminal span-based prototypical network that tackles few-shot NER . they transform sequential tags into a global boundary matrix and use prototypical learning . |
| Outcome: | The proposed model outperforms strong baselines over multiple benchmarks. |
Distributional Surgery for Language Model Activations (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Language models can produce undesirable outputs including harmful or toxic outputs. |
| Approach: | They propose a method to detect undesirable content using activations . they propose layerwise distributional steering policies that transform the attention heads . |
| Outcome: | The proposed method outperforms baselines in reducing undesirable output generation. |
BiasGuard: A Reasoning-Enhanced Bias Detection Tool for Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for identifying bias in LLM-generated content face limitations . existing methods rely on pattern-based learning, which makes it challenging to understand intentions . |
| Approach: | They propose a bias detection tool that explicitly analyzes inputs and reasons through fairness specifications to provide accurate judgments. |
| Outcome: | The proposed tool outperforms existing tools and improves accuracy and reduces over-fairness misjudgments. |
Depth Growing for Neural Machine Translation (P19-1)
Copied to clipboard
| Challenge: | Neural machine translation models with tens and even more than a hundred blocks have shown effectiveness in image recognition. |
| Approach: | They propose a two-stage approach with three specially designed components to construct deeper NMT models. |
| Outcome: | The proposed approach improves on WMT14 EnglishGerman and EnglishFrench translation tasks. |
Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Reinforcement learning from human feedback (RLHF) is the primary method for aligning large language models with human preferences. |
| Approach: | They propose to train an Absolute-Rating Multi-Objective Reward Model with multi-dimensional absolute-rating data. |
| Outcome: | The proposed model outperforms the LLM-as-a-judge method on RewardBench . it achieves state-of-the-art performance on the benchmark . |
Sycophancy Mitigation Through Reinforcement Learning with Uncertainty-Aware Adaptive Reasoning Trajectories (2025.emnlp-main)
Copied to clipboard
Mohammad Beigi, Ying Shen, Parshin Shojaee, Qifan Wang, Zichao Wang, Chandan K. Reddy, Ming Jin, Lifu Huang
| Challenge: | Existing studies show that large language models inadvertently foster sycophancy . scophancies are a tendency of models to blindly conform to user preferences without critical reasoning or self-reflection. |
| Approach: | They propose a method to reduce sycophancy by combining uncertainty-aware Monte Carlo tree search and progress-based reinforcement learning. |
| Outcome: | The proposed model outperforms baseline models in effectively reducing sycophancy while maintaining performance on out-of-distribution inputs. |
Knowing False Negatives: An Adversarial Training Method for Distantly Supervised Relation Extraction (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for relation extraction ignore the incompleteness of existing knowledge bases . current methods are too weak and cause noises when training and testing are not based on training data. |
| Approach: | They propose a method to automatically align unstructured text with relation instances in a knowledge base . they use heuristics to leverage the memory mechanism of deep neural networks to find out possible FN samples . |
| Outcome: | Experiments on two wildly-used benchmark datasets show the effectiveness of the proposed method. |
Generate then Refine: Data Augmentation for Zero-shot Intent Detection (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing data augmentation methods rely on few labelled examples for each intent category, which can be expensive in settings with many possible intents. |
| Approach: | They propose a data augmentation method for intent detection in zero-resource domains by using an open-source large language model and a smaller sequence-to-sequence model. |
| Outcome: | The proposed method significantly improves the data utility and diversity over the zero-shot LLM baseline for unseen domains and over common baseline approaches. |
SPILL: Domain-Adaptive Intent Clustering based on Selection and Pooling with Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for intent clustering rely on labeled examples or unsupervised fine-tuning to optimize results for each new dataset. |
| Approach: | They propose a method that uses an embedder to derive an embedding for each utterance and then pool them with the seed to improve the embeddable results. |
| Outcome: | The proposed method outperforms embedding methods and is comparable to state-of-the-art methods. |
Learn and Consolidate: Continual Adaptation for Zero-Shot and Multilingual Neural Machine Translation (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing multilingual neural machine translation models perform poorly on language pairs with no parallel corpus. |
| Approach: | They propose a two-stage approach that encourages original models to acquire language-agnostic multilingual representations from new data and preserves the model architecture without introducing parameters. |
| Outcome: | The proposed approach improves performance in translation directions where existing models are weak and mitigates degeneration in the well-performing translation directions, offering flexibility in the real-world scenario. |
Community-Aware Assessment of Social Textual Engagement and Resonance: A Human-Centric Perspective on User-Generated Content Evaluation (2026.acl-long)
Copied to clipboard
| Challenge: | Traditional Video Quality Assessment (VQA) focuses on aesthetic fidelity and technical distortions. |
| Approach: | They propose a new task that evaluates whether a UGC item has positive community resonance based on multimodal attributes rather than visual quality alone. |
| Outcome: | The proposed task outperforms state-of-the-art baselines on CASTER-Bench . it provides interpretable and empathetic reasoning paths that align with real community feedback. |
TECA: A Two-stage Approach with Controllable Attention Soft Prompt for Few-shot Nested Named Entity Recognition (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods for few-shot nested named entity recognition (NER) ignore relationship between inner and outer entities, which is crucial for fewshot ner. |
| Approach: | They propose a span-based method with a controllable attention soft prompt for few-shot nested named entity recognition (TECA) the span part identification provides possible entity mentions without an extra filtering module. |
| Outcome: | The proposed method outperforms baseline models on four benchmark datasets and outperformed competing models on F1-score by 5.62% on ACE04, 5.11% on ace05, 3.41% on KBP2017 and 0.7% on GENIA on the 10-shot setting. |
PictoEduca: Building a Dataset for Spanish Text-to-Pictogram Generation (2026.findings-acl)
Copied to clipboard
| Challenge: | PictoEduca is the first large-scale Spanish text-to-pictogram dataset for augmentative and alternative communication. |
| Approach: | They present PictoEduca, a large-scale Spanish text-to-pictogram dataset for augmentative and alternative communication. |
| Outcome: | The proposed dataset combines automatic annotation with targeted expert correction, supporting scalable and high-quality corpus construction. |
Introducing Spotlight: A Novel Approach for Generating Captivating Key Information from Documents (2025.emnlp-main)
Copied to clipboard
Ankan Mullick, Sombit Bose, Rounak Saha, Ayan Kumar Bhowmick, Aditya Vempaty, Prasenjit Dey, Ravi Kokku, Pawan Goyal, Niloy Ganguly
| Challenge: | Unlike highlights (fragmented key points) and traditional summaries, spotlights selectively emphasize intriguing content to foster deeper reader engagement with the source material. |
| Approach: | They propose a novel paradigm for information extraction that selectively emphasizes intriguing content to foster deeper reader engagement with the source material. |
| Outcome: | The proposed model improves readability and boosts engagement value of the original document. |