Papers by Giorgos Filandrianos
Bias Beware: The Impact of Cognitive Biases on LLM-Driven Product Recommendations (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have revolutionized product recommenders, but their susceptibility to adversarial manipulations is difficult to detect. |
| Approach: | They propose to use large language models to investigate cognitive biases as adversarial strategies in product research using LLMs. |
| Outcome: | The proposed approach is the first to tap into human psychological principles, making such manipulations hard to detect. |
Counterfactuals of Counterfactuals: a back-translation-inspired approach to analyse counterfactual editors (2023.findings-acl)
Copied to clipboard
George Filandrianos, Edmund Dervakos, Orfeas Menis Mastromichalakis, Chrysoula Zerva, Giorgos Stamou
| Challenge: | Existing explanations for classifiers are counterfactual or contrastive . lack of universal ground truth for counterf actual edits hinders their evaluation . |
| Approach: | They propose a back translation-inspired evaluation methodology that utilises earlier outputs of the explainer as ground truth proxies to investigate the consistency of explainers. |
| Outcome: | The proposed method can provide valuable insights into the behaviour of predictor and explainer models and infer patterns that would otherwise be obscured. |
RISCORE: Enhancing In-Context Riddle Solving in Language Models through Context-Reconstructed Example Augmentation (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods for prompting Large Language Models (LLMs) are lacking in advanced reasoning skills. |
| Approach: | They propose a method that generates and utilizes contextually reconstructed sentences to generate few-shot exemplars. |
| Outcome: | The proposed method significantly improves the performance of large language models in vertical and lateral thinking tasks, surpassing traditional exemplar selection strategies across a variety of few-shot settings. |
PAKTON: A Multi-Agent Framework for Question Answering in Long Legal Agreements (2025.emnlp-main)
Copied to clipboard
| Challenge: | Contract review is a complex and time-intensive task that typically requires legal expertise. |
| Approach: | a new open-source contract review framework is designed to handle complexities of contract analysis . PAKTON is a retrieval-augmented generation framework with plug-and-play capabilities . |
| Outcome: | The open-source framework outperforms models in predictive accuracy, retrieval performance, explainability, completeness, and grounded justifications. |
”I Never Said That”: A dataset, taxonomy and baselines on response clarity classification (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Equivocation and ambiguity in public speech are well-studied discourse phenomena . a new taxonomy aims to detect and classify response clarity in political interviews . |
| Approach: | They propose a taxonomy that uses Large Language Models and human annotations to detect and classify response clarity in political interviews. |
| Outcome: | The proposed taxonomy combines ChatGPT and human annotations to identify clarity in political questions . it provides a fine-grained taxonomies for evasion techniques related to unclear, ambiguous responses . |
Pitfalls of Scale: Investigating the Inverse Task of Redefinition in Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have shown remarkable results in several linguistic, reasoning and knowledge retrieval tasks. |
| Approach: | They propose to scale Large Language Models (LLMs) to scale up to reveal potential reasoning gaps as LLMs scale up. |
| Outcome: | The proposed redefinition task shows that model performance degrades with scale, and false confidence rises. |
Puzzle Solving using Reasoning of Large Language Models: A Survey (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models (LLMs) have demonstrated their logical reasoning abilities across various domains. |
| Approach: | They propose to divide puzzles into rule-based and rule-less categories and critically assess LLMs' performance through various methodologies. |
| Outcome: | The proposed models have demonstrated capabilities in deductive reasoning and inductive reasoning, but they face limitations in inductive thinking. |
Assumed Identities: Quantifying Gender Bias in Machine Translation of Gender-Ambiguous Occupational Terms (2025.emnlp-main)
Copied to clipboard
| Challenge: | ailsntua researchers examine whether machine translation systems exhibit gender biases that reinforce societal stereotypes. |
| Approach: | They propose a probability-based metric to evaluate gender bias by analyzing aggregated model responses. |
| Outcome: | The proposed metric evaluates whether translations in Greek and French align with or diverge from societal stereotypes. |