Papers by Maria Maistro
Culinary Crossroads: A RAG Framework for Enhancing Diversity in Cross-Cultural Recipe Adaptation (2026.acl-long)
Copied to clipboard
| Challenge: | Retrieval-augmented generation (RAG) is a promising approach for cross-cultural recipe adaptation, but it fails to generate diverse results even when provided with varied contextual inputs. |
| Approach: | They propose a plug-and-play RAG framework that enhances diversity in both retrieval and context organization to generate diverse outputs to accommodate multiple user preferences. |
| Outcome: | The proposed framework achieves Pareto efficiency in terms of diversity and quality of recipe adaptation compared to closed-book LLMs. |
DYNAMICQA: Tracing Internal Knowledge Conflicts in Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | LMs are useful in a variety of downstream applications from summarization to fact-checking, often relying on factual knowledge memorized during pre-training. |
| Approach: | They use two knowledge conflict measures and a novel dataset DYNAMICQA to examine the effect of intra-memory conflict on LMs' ability to accept contextual knowledge. |
| Outcome: | The proposed model can accept contextual knowledge with a higher degree of accuracy than models with fewer truth values. |
Normalized AOPC: Fixing Misleading Faithfulness Metrics for Feature Attributions Explainability (2025.acl-long)
Copied to clipboard
Joakim Edin, Andreas Geert Motzfeldt, Casper L. Christensen, Tuukka Ruotsalo, Lars Maaløe, Maria Maistro
| Challenge: | Deep neural network predictions are notoriously difficult to interpret due to the difficulty in understanding their inner mechanisms. |
| Approach: | They propose to normalize AOPC to enable consistent cross-model evaluations and more meaningful interpretation of individual scores. |
| Outcome: | The proposed approach can radically change AOPC results, questioning the conclusions of earlier studies and offering a more robust framework for assessing feature attribution faithfulness. |
Bridging Cultures in the Kitchen: A Framework and Benchmark for Cross-Cultural Recipe Retrieval (2024.emnlp-main)
Copied to clipboard
| Challenge: | Adapting recipes to cultural differences presents significant importance and challenges . bridging cultural differences is a challenge, but IR can help. |
| Approach: | They propose a framework that preserves the original recipe and its cultural appropriateness for the target culture. |
| Outcome: | The proposed framework preserves the original recipe and its cultural appropriateness for the target culture while maintaining relevance to the original. |
An Unsupervised Approach to Achieve Supervised-Level Explainability in Healthcare Records (2024.emnlp-main)
Copied to clipboard
| Challenge: | State-of-the-art explainability methods rely on human annotations, which are costly. |
| Approach: | They propose an approach to produce plausible and faithful explanations without annotations . they use adversarial robustness training to improve plausibility and AttInGrad . |
| Outcome: | The proposed method produces plausible explanations without human annotations on a medical coding task. |
A Reality Check on Context Utilisation for Retrieval-Augmented Generation (2025.acl-long)
Copied to clipboard
Lovisa Hagström, Sara Vera Marjanovic, Haeun Yu, Arnav Arora, Christina Lioma, Maria Maistro, Pepa Atanasova, Isabelle Augenstein
| Challenge: | Existing studies on LM context utilisation of retrieved information have focused on synthetic text. |
| Approach: | They propose a dataset of unreliable, insufficient and difficult-to-understand contexts with real-world queries and contexts manually annotated for stance to compare them to synthetic datasets. |
| Outcome: | The proposed model outperforms synthetic datasets and exaggerates rare context characteristics, leading to inflated context utilisation results. |
How Context Shapes Truth: Geometric Transformations of Statement-level Truth Representations in LLMs (2026.acl-long)
Copied to clipboard
| Challenge: | Prior work shows that large language models encode whether a statement is true as a vector in residual stream activations. |
| Approach: | They study how truth vectors change when context is introduced in Large Language Models . they measure directional change between truth vector with and without context and relative magnitude of truth vector upon adding context. |
| Outcome: | The results show that large models distinguish relevant from irrelevant context mainly through directional change () |
As easy as PIE: understanding when pruning causes language models to disagree (2025.findings-naacl)
Copied to clipboard
| Challenge: | Language Model pruning reduces the model's efficiency by removing weights, nodes, or other parts of its architecture. |
| Approach: | They propose to prune Language Models (LMs) to produce smaller, hence more efficient models with small loss to their effectiveness. |
| Outcome: | The proposed pruning method hurts data points that matter the most when pruning . the proposed pruning technique is based on a new study of NLP datasets . |