Riddle-solving requires advanced reasoning skills, pushing Large Language Models (LLMs) to engage in abstract thinking and creative problem-solving, often revealing limitations in their cognitive abilities. In this paper, we examine the riddle-solving capabilities of LLMs using a multiple-choice format, exploring how different prompting techniques impact performance on riddles that demand diverse reasoning skills. To enhance results, we introduce RISCORE (RIddle Solving with COntext REcontruciton) a novel fully automated prompting method that generates and utilizes contextually reconstructed sentence-based puzzles in conjunction with the original examples to create few-shot exemplars. Our experiments demonstrate that RISCORE significantly improves the performance of language models in both vertical and lateral thinking tasks, surpassing traditional exemplar selection strategies across a variety of few-shot settings.

Multilingual hallucination detection stands as an underexplored challenge, which the Mu-SHROOM shared task seeks to address. In this work, we propose an efficient, training-free LLM prompting strategy that enhances detection by translating multilingual text spans into English. Our approach achieves competitive rankings across multiple languages, securing two first positions in low-resource languages. The consistency of our results highlights the effectiveness of our translation strategy for hallucination detection, demonstrating its applicability regardless of the source language.

The {textit{Unlearning Sensitive Content from Large Language Models}} task aims to remove targeted datapoints from trained models while minimally affecting their general knowledge. In our work, we leverage parameter-efficient, gradient-based unlearning using low-rank (LoRA) adaptation and layer-focused fine-tuning. To further enhance unlearning effectiveness, we employ data chunking, splitting forget data into disjoint partitions and merging them with cyclically sampled retain samples at a pre-defined ratio. Our task-agnostic method achieves an outstanding forget-retain balance, ranking first on leaderboards and significantly outperforming baselines and competing systems.

In this paper, we present our submission to SemEval-2025 Task 8: Question Answering over Tabular Data. This task, evaluated on the DataBench dataset, assesses Large Language Models’ (LLMs) ability to answer natural language questions over structured data while addressing topic diversity and table size limitations in previous benchmarks. We propose a system that employs effective LLM prompting to translate natural language queries into executable code, enabling accurate responses, error correction, and interpretability. Our approach ranks first in both subtasks of the competition in the proprietary model category, significantly outperforming the organizer’s baseline.

In this paper, we present our team’s submissions for SemEval-2024 Task-6 - SHROOM, a Shared-task on Hallucinations and Related Observable Overgeneration Mistakes. The participants were asked to perform binary classification to identify cases of fluent overgeneration hallucinations. Our experimentation included fine-tuning a pre-trained model on hallucination detection and a Natural Language Inference (NLI) model. The most successful strategy involved creating an ensemble of these models, resulting in accuracy rates of 77.8% and 79.9% on model-agnostic and model-aware datasets respectively, outperforming the organizers’ baseline and achieving notable results when contrasted with the top-performing results in the competition, which reported accuracies of 84.7% and 81.3% correspondingly.

In this paper, we outline our submission for the SemEval-2024 Task 9 competition: ‘BRAINTEASER: A Novel Task Defying Common Sense’. We engage in both sub-tasks: Sub-task A-Sentence Puzzle and Sub-task B-Word Puzzle. We evaluate a plethora of pre-trained transformer-based language models of different sizes through fine-tuning. Subsequently, we undertake an analysis of their scores and responses to aid future researchers in understanding and utilizing these models effectively. Our top-performing approaches secured competitive positions on the competition leaderboard across both sub-tasks. In the evaluation phase, our best submission attained an average accuracy score of 81.7% in the Sentence Puzzle, and 85.4% in the Word Puzzle, significantly outperforming the best neural baseline (ChatGPT) by more than 20% and 30% respectively.

In the wake of responsible AI, interpretability methods, which attempt to provide an explanation for the predictions of neural models have seen rapid progress. In this work, we are concerned with explanations that are applicable to natural language processing (NLP) models and tasks, and we focus specifically on the analysis of counterfactual, contrastive explanations. We note that while there have been several explainers proposed to produce counterfactual explanations, their behaviour can vary significantly and the lack of a universal ground truth for the counterfactual edits imposes an insuperable barrier on their evaluation. We propose a new back translation-inspired evaluation methodology that utilises earlier outputs of the explainer as ground truth proxies to investigate the consistency of explainers. We show that by iteratively feeding the counterfactual to the explainer we can obtain valuable insights into the behaviour of both the predictor and the explainer models, and infer patterns that would be otherwise obscured. Using this methodology, we conduct a thorough analysis and propose a novel metric to evaluate the consistency of counterfactual generation approaches with different characteristics across available performance indicators.