Papers by Akbar Karimi
Explainable Hallucination through Natural Language Inference Mapping (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) often generate hallucinated content, making it crucial to identify and quantify inconsistencies in their outputs. |
| Approach: | They propose a framework that maps entailment and contradiction relations between inputs and outputs using a natural language inference model. |
| Outcome: | The proposed framework outperforms state-of-the-art methods by five percentage points while providing clear, interpretable explanations. |
Extracting an English-Persian Parallel Corpus from Comparable Corpora (L18-1)
Copied to clipboard
| Challenge: | Existing methods to extract parallel sentences from Wikipedia are limited for some language pairs such as Persian-English. |
| Approach: | They propose a bidirectional method to extract parallel sentences from Wikipedia . they add extracted sentences to existing training data and use IR system to measure similarity . |
| Outcome: | The proposed method outperforms the one-directional approach in analyzing translation data from two translation systems and IR systems. |
Aspect-Based Emotion Analysis and Multimodal Coreference: A Case Study of Customer Comments on Adidas Instagram Posts (2022.lrec-1)
Copied to clipboard
| Challenge: | Aspect-based sentiment analysis of user-generated content has been relatively unexplored in recent years. |
| Approach: | They present a multimodal dataset for Aspect-Based Emotion Analysis (ABEA) they take the first steps in investigating the utility of multimodal coreference resolution in an ABEA framework. |
| Outcome: | The proposed dataset consists of 4,900 comments on 175 images and is annotated with aspect and emotion categories and the emotional dimensions of valence and arousal. |
More Agents Improve Math Problem Solving but Adversarial Robustness Gap Persists (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are powerful but weak when inputs are perturbed. |
| Approach: | They evaluate LLMs that are more powerful than single LLM in math question answering . they use a unified sampling-and-voting framework to evaluate their models . |
| Outcome: | The proposed models show that collaboration between agents improves accuracy and clean accuracy even with a large number of agents. |
AEDA: An Easier Data Augmentation Technique for Text Classification (2021.findings-emnlp)
Copied to clipboard
| Challenge: | AEDA is an easier data augmentation technique than EDA. |
| Approach: | They propose an augmentation technique that includes only random insertion of punctuation marks into the original text. |
| Outcome: | The proposed method is easier to implement for data augmentation than EDA method. |
Multi-Hop Reasoning for Question Answering with Hyperbolic Representations (2025.findings-acl)
Copied to clipboard
| Challenge: | a rigorous and detailed comparison of the two spaces for multi-hop reasoning is lacking. |
| Approach: | They compare the capacity of hyperbolic space versus Euclidean space in multi-hop reasoning . they use an encoder-decoder model to integrate hyperbolical representations with a knowledge graph . |
| Outcome: | The proposed model outperforms the Euclidean space in multi-hop reasoning. |