Papers by Faegheh Hasibi
Real World Conversational Entity Linking Requires More Than Zero-Shots (2024.findings-acl)
Copied to clipboard
| Challenge: | Entity linking (EL) in conversations is a key component of many downstream tasks such as semantic search. |
| Approach: | They propose to use Fandom and Wikipedia to evaluate EL models' ability to generalize to a new unfamiliar KB without prior training. |
| Outcome: | The proposed evaluation framework and dataset are tailored to facilitate the study. |
Why Uncertainty Estimation Methods Fall Short in RAG: An Axiomatic Analysis (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing UE methods cannot reliably estimate the correctness of LLM responses in Retrieval-Augmented Generation (RAG) . Existing methods generate low uncertainty values without considering relevance of context to query . |
| Approach: | They propose an axiomatic framework to identify deficiencies in existing UE methods and introduce five constraints that an effective UE method should meet after incorporating retrieved documents into the LLM’s prompt. |
| Outcome: | The proposed framework satisfies all the axioms and improves correlation between uncertainty estimates and correctness. |
SPILL: Domain-Adaptive Intent Clustering based on Selection and Pooling with Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for intent clustering rely on labeled examples or unsupervised fine-tuning to optimize results for each new dataset. |
| Approach: | They propose a method that uses an embedder to derive an embedding for each utterance and then pool them with the seed to improve the embeddable results. |
| Outcome: | The proposed method outperforms embedding methods and is comparable to state-of-the-art methods. |
Find the Funding: Entity Linking with Incomplete Funding Knowledge Bases (2022.coling-1)
Copied to clipboard
| Challenge: | Existing approaches to identifying and linking funding entities are suboptimal for the funding domain. |
| Approach: | They propose an entity linking model that can perform NIL prediction and overcome data scarcity issues in a time and data-efficient manner. |
| Outcome: | The proposed model outperforms existing baselines and overcomes data scarcity issues in a time and data-efficient manner. |
LLMs Enable Bag-of-Texts Representations for Short-Text Clustering (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for short text clustering require labeling and no embeddings optimization. |
| Approach: | They propose a training-free method for unsupervised short text clustering that relies less on careful selection of embedders than other methods. |
| Outcome: | The proposed method achieves comparable or superior results to state-of-the-art methods, but without embeddings optimization or prior knowledge of clusters or labels. |
Generate then Refine: Data Augmentation for Zero-shot Intent Detection (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing data augmentation methods rely on few labelled examples for each intent category, which can be expensive in settings with many possible intents. |
| Approach: | They propose a data augmentation method for intent detection in zero-resource domains by using an open-source large language model and a smaller sequence-to-sequence model. |
| Outcome: | The proposed method significantly improves the data utility and diversity over the zero-shot LLM baseline for unseen domains and over common baseline approaches. |