Papers with structured framework
Continual Learning of Large Language Models (2025.emnlp-tutorials)
Copied to clipboard
| Challenge: | This tutorial explores the challenges of continual learning in large language models . participants will learn strategies to mitigate forgetting and manage data and evaluation pipelines . |
| Approach: | This tutorial offers a comprehensive exploration of continual learning in the context of large language models. |
| Outcome: | This tutorial explores the challenges of continual learning in large language models . participants will learn how to manage data and evaluation pipelines and adapt responsibly . |
A Dual-Layered Evaluation of Geopolitical and Cultural Bias in LLMs (2025.acl-srw)
Copied to clipboard
| Challenge: | Large language models exhibit cultural and geopolitical biases when their outputs shape public opinion or reinforce dominant narratives. |
| Approach: | They define two types of bias in large language models: model bias and inference bias through a two-phase evaluation. |
| Outcome: | The proposed framework evaluates large language models on factual and disputable questions across four languages and question types. |
Entity Exchange in the Wild: A Diagnostic Study of LLM Based Real-World Conversational Entity Extraction (2026.acl-industry)
Copied to clipboard
| Challenge: | Prior work has examined the impact of transcription noise and cross-turn reasoning, but it has not systematically analyzed how entity-exchange phenomena themselves shape extraction performance. |
| Approach: | They evaluate 16 large language models on 6,387 real-world customer–agent conversations spanning 12 entity types across numeric, alphanumeric, temporal, and free-text categories. |
| Outcome: | The proposed model improves on the extracted entities across all three axes yielding average gains of up to 6.4% across models. |
Tree-of-Quote Prompting Improves Factuality and Attribution in Multi-Hop and Medical Reasoning (2025.emnlp-main)
Copied to clipboard
Justin Xu, Yiming Li, Zizheng Zhang, Augustine Yui Hei Luk, Mayank Jobanputra, Samarth Oza, Ashley Murray, Meghana Reddy Kasula, Andrew Parker, David W Eyre
| Challenge: | Large language models (LLMs) produce fluent but factually incorrect outputs, a phenomenon commonly referred to as hallucination. |
| Approach: | They propose a Tree-of-Quote framework that decomposes complex questions into subquestions and generates quotes to support each step without retrieval. |
| Outcome: | Experiments on StrategyQA, 2WikiMultiHopQA, MuSiQue, MoreHopQ, and MedQA show that ToQ improves factuality and attribution over baselines. |
Retrieval Enhanced Feedback via In-context Neural Error-book (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for learning from errors lack a structured framework for analyzing and mitigating errors, especially in Multimodal Large Language Models (MLLMs). |
| Approach: | They propose a teacher-student framework that systematically structures errors to deliver targeted feedback for multimodal reasoning. |
| Outcome: | The proposed framework improves inference efficiency, token usage, and scalability by building a query-based structure that prioritizes visual information, diagnoses failure points, and guides corrective actions. |
Leveraging Large Language Models for NLG Evaluation: Advances and Challenges (2024.emnlp-main)
Copied to clipboard
| Challenge: | introducing Large Language Models (LLMs) has opened new avenues for assessing generated content quality, e.g., coherence, creativity, and context relevance. |
| Approach: | They propose a taxonomy for organizing existing LLM-based evaluation metrics and a structured framework to understand and compare them. |
| Outcome: | The proposed taxonomy offers a framework to understand and compare LLM-based evaluation methods. |
Creativity in LLM-based Multi-Agent Systems: A Survey (2025.emnlp-main)
Copied to clipboard
Yi-Cheng Lin, Kang-Chieh Chen, Zhe-Yan Li, Tzu-Heng Wu, Tzu-Hsuan Wu, Kuan-Yu Chen, Hung-yi Lee, Yun-Nung Chen
| Challenge: | Large language model (LLM)-driven multi-agent systems (MAS) are transforming how humans and AIs collaboratively generate ideas and artifacts. |
| Approach: | They present a taxonomy of agent proactivity and persona design and an overview of generation techniques. |
| Outcome: | The proposed framework and roadmap offers a roadmap for advancing the development, evaluation, and standardization of creative MAS. |
DiNaM: Disinformation Narrative Mining with Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Disinformation is a powerful force in digital media, posing serious threats such as physical harm and the erosion of democracy. |
| Approach: | They propose to use a multi-step approach to uncover disinformation narratives by using Large Language Models to detect false information and then using clustering techniques to identify underlying disinformation stories. |
| Outcome: | The proposed algorithm outperforms general-purpose narrative mining methods by 16.4–24.7%. |
Multilingual Dialogue Generation and Localization with Dialogue Act Scripting (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to training or evaluating non-English dialogue datasets often introduce artifacts that reduce their naturalness and cultural appropriateness. |
| Approach: | They propose a structured framework for encoding, localizing, and generating multilingual dialogues from abstract intent representations. |
| Outcome: | The proposed framework outperforms translation models in Italian, German, and Chinese on cultural relevance, coherence, and situational appropriateness. |
TAIGR: Towards Modeling Influencer Content on Social Media via Structured, Pragmatic Inference (2026.acl-long)
Copied to clipboard
| Challenge: | Health influencers are often conveyed through conversational narratives and rhetorical strategies rather than explicit factual claims. |
| Approach: | They propose a framework to analyze influencer discourse using takeaway argumentation inference with Grounded References. |
| Outcome: | The proposed framework is based on a content validation task over influencer video transcripts on health, showing that accurate validation requires modeling the discourse’s pragmatic and argumentative structure rather than treating transcripts as flat collections of claims. |
SocraticKG: Knowledge Graph Construction via QA-Driven Fact Extraction (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to construct knowledge graphs struggle with factual coverage and information loss. |
| Approach: | They propose an automated KG construction method that introduces question-answer pairs as a structured intermediate representation to unfold document-level semantics prior to triple extraction. |
| Outcome: | The proposed method achieves superior factual retention while maintaining high structural cohesion even as extracted knowledge volume substantially expands. |