Consistent Joint Decision-Making with Heterogeneous Learning Models (2024.findings-eacl)
Copied to clipboard
| Challenge: | Existing approaches to handle inconsistencies in correlated decisions are insufficient for tasks like hierarchical image classification and text summa-rization. |
| Approach: | They propose a decision-making framework that promotes consistency among decisions made by diverse models while utilizing external knowledge. |
| Outcome: | The proposed framework is superior to baselines on multiple datasets. |
Similar Papers
Towards Multi-Perspective NLP Systems: A Thesis Proposal (2025.acl-srw)
Copied to clipboard
| Challenge: | Existing approaches to resolving disagreements ignore individual opinions and can result in the marginalization of minority perspectives. |
| Approach: | They propose to preserve individual labels in human-annotated datasets for subjective tasks and propose solutions for developing Perspective-Aware by design systems. |
| Outcome: | The proposed framework will be used to develop more responsible and inclusive models. |
Seeing All Sides: Multi-Perspective In-Context Learning for Subjective NLP (2026.findings-eacl)
Copied to clipboard
| Challenge: | Modern language models excel at factual reasoning but struggle with value diversity, authors say . task-sensitive tasks such as hate speech expose this limitation . human disagreement captures the diversity of plausible human perspectives, authors argue . |
| Approach: | They evaluate four large language models with human disagreements on five datasets . they find multi-perspective in-context learning outperforms standard prompting . |
| Outcome: | The proposed approach outperforms standard prompting on English labels while disaggregated soft predictions better align with human judgments in Arabic and Italian datasets. |
DVMap: Fine-Grained Pluralistic Value Alignment via High-Consensus Demographic-Value Mapping (2026.acl-long)
Copied to clipboard
| Challenge: | Current Large Language Models (LLMs) rely on coarse-grained national labels for pluralistic value alignment. |
| Approach: | They propose a framework for fine-grained pluralistic value alignment using demographic constraints. |
| Outcome: | The proposed framework can identify groups with predictable, high-consensus value preference . it achieves 48.6% accuracy, surpassing open-source LLM DeepSeek-v3.2 . |
Probability-Consistent Preference Optimization for Enhanced LLM Reasoning (2025.findings-acl)
Copied to clipboard
Yunqiao Yang, Houxing Ren, Zimu Lu, Ke Wang, Weikang Shi, Aojun Zhou, Junting Pan, Mingjie Zhan, Hongsheng Li
| Challenge: | Recent advances in preference optimization have demonstrated significant potential for improving mathematical reasoning capabilities in large language models. |
| Approach: | They propose a framework that establishes two quantitative metrics for preference selection: surface-level answer correctness and intrinsic token-level probability consistency. |
| Outcome: | The proposed framework outperforms existing outcome-only criterion approaches across a diverse range of LLMs and benchmarks. |
Carefully Considering Culture: Analyzing LLM Alignment in Single- and Multi-Cultural Settings using Cultural Consensus Theory (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent work in NLP has examined large language models for their understanding of cultural norms across countries, ignoring group consensus or possible multicultural environments. |
| Approach: | They apply cultural consensus theory to the World Values Survey to model multidimensional nuance by ignoring group consensus or over-regularizing consensus. |
| Outcome: | The proposed model misrepresents cultural structures by failing to form cohesive consensus or severely over-regularizing consensus. |
Striking a Balance: Alleviating Inconsistency in Pre-trained Models for Symmetric Classification Tasks (2022.findings-acl)
Copied to clipboard
| Challenge: | Inconsistency is observed in symmetric classification tasks that take two inputs and require the output to be invariant of the order of the inputs. |
| Approach: | They propose a consistency loss function to alleviate inconsistency in symmetric classification tasks that take two inputs and require the output to be invariant of the order of the inputs. |
| Outcome: | The proposed model improves consistency in predictions for three paraphrase detection datasets without significant drop in accuracy scores. |
Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019) (D19-61)
Copied to clipboard
| Challenge: | EMNLP-IJCNLP 2019 Workshop on Deep Learning Approaches for Low-Resource Natural Language Processing takes place in Hong Kong, China . |
| Approach: | EMNLP-IJCNLP 2019 Workshop on Deep Learning Approaches for Low-Resource Natural Language Processing takes place in Hong Kong, China . call for papers for this second workshop met with a strong response . |
| Outcome: | the EMNLP-IJCNLP 2019 workshop on deep learning approaches for low-resource natural language processing takes place in Hong Kong, China. |
The Hidden Strength of Disagreement: Unraveling the Consensus-Diversity Tradeoff in Adaptive Multi-Agent Systems (2025.emnlp-main)
Copied to clipboard
| Challenge: | Conventional LLM-based MAS rely on explicit coordination, e.g., prompts or voting, risking premature homogenization. |
| Approach: | They propose to preserve partial diversity by combining in-context learning with explicit coordination to form consensus in dynamic environments. |
| Outcome: | The proposed model outperforms explicit consensus models on three scenarios showing that partial deviation from group norms boosts exploration, robustness, and performance. |
Make Your Decision Convincing! A Unified Two-Stage Framework: Self-Attribution and Decision-Making (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing frameworks for explaining black-box model behavior are unreliable . large-scale pre-trained models often rely on superficial clues for predictions . |
| Approach: | They propose a unified two-stage framework that uses subsequences from the input text as a rationale to generate model decision. |
| Outcome: | The proposed framework achieves competitive results on five reasoning datasets and in semi-supervised scenarios. |
Interlocking-free Selective Rationalization Through Genetic-based Learning (2025.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to selective rationalization suffer from interlocking, a phenomenon known as interlock. |
| Approach: | They propose a genetically-based disjoint training architecture for selective rationalization that avoids interlocking by performing genetic global search. |
| Outcome: | The proposed model outperforms state-of-the-art models on a synthetic and real-world benchmark. |