Anum Afzal

19 papers A* 1Misc 1Journal 10Unranked 7
YearRankTypeTitle / Venue / Authors
2026 — conf
Beyond Grid Search: Leveraging Bayesian Optimization for Accelerating RAG Pipeline Optimization.
EACL (Industry Track)
Anum Afzal, Xueru Zheng, Florian Matthes
2026 J jnl
Real-Time Generation of Game Video Commentary with Multimodal LLMs: Pause-Aware Decoding Approaches.
CoRR
Anum Afzal, Yuki Saito, Hiroya Takamura, Katsuhito Sudoh, Shinnosuke Takamichi, Graham Neubig, Florian Matthes, Tatsuya Ishigaki
2025 J jnl
Can Smaller LLMs do better? Unlocking Cross-Domain Potential through Parameter-Efficient Fine-Tuning for Text Summarization.
CoRR
Anum Afzal, Mehul Kumawat, Florian Matthes
2025 Misc conf
Candidate Profile Summarization: A RAG Approach with Synthetic Data Generation for Tech Jobs.
RANLP
Anum Afzal, Ishwor Subedi, Florian Matthes
2025 A* conf
DA-Pred: Performance Prediction for Text Summarization under Domain-Shift and Instruct-Tuning.
EMNLP
Anum Afzal, Florian Matthes, Alexander R. Fabbri
2025 — conf
FActBench: A Benchmark for Fine-grained Automatic Evaluation of LLM-Generated Text in the Medical Domain.
ICNLSP
Anum Afzal, Juraj Vladika, Florian Matthes
2025 J jnl
FActBench: A Benchmark for Fine-grained Automatic Evaluation of LLM-Generated Text in the Medical Domain.
CoRR
Anum Afzal, Juraj Vladika, Florian Matthes
2025 J jnl
JaccDiv: A Metric and Benchmark for Quantifying Diversity of Generated Marketing Text in the Music Industry.
CoRR
Anum Afzal, Alexandre Mercier, Florian Matthes
2025 — conf
Knowing Before Saying: LLM Representations Encode Information About Chain-of-Thought Success Before Completion.
ACL (Findings)
Anum Afzal, Florian Matthes, Gal Chechik, Yftah Ziser
2025 J jnl
Knowing Before Saying: LLM Representations Encode Information About Chain-of-Thought Success Before Completion.
CoRR
Anum Afzal, Florian Matthes, Gal Chechik, Yftah Ziser
2024 — conf
A Semi-Automatic Light-Weight Approach Towards Data Generation for a Domain-Specific FAQ Chatbot Using Human-in-the-Loop.
ICAART (3)
Anum Afzal, Tao Xiang, Florian Matthes
2024 J jnl
AdaptEval: Evaluating Large Language Models on Domain Adaptation for Text Summarization.
CoRR
Anum Afzal, Ribin Chalumattu, Florian Matthes, Laura Mascarell
2024 — conf
Towards Optimizing a Retrieval Augmented Generation using Large Language Model on Academic Data.
NLPIR
Anum Afzal, Juraj Vladika, Gentrit Fazlija, Andrei Staradubets, Florian Matthes
2024 J jnl
Towards Optimizing a Retrieval Augmented Generation using Large Language Model on Academic Data.
CoRR
Anum Afzal, Juraj Vladika, Gentrit Fazlija, Andrei Staradubets, Florian Matthes
2024 J jnl
Towards Optimizing and Evaluating a Retrieval Augmented QA Chatbot using LLMs with Human in the Loop.
CoRR
Anum Afzal, Alexander Kowsik, Rajna Fani, Florian Matthes
2023 — conf
Challenges in Domain-Specific Abstractive Summarization and How to Overcome Them.
ICAART (3)
Anum Afzal, Juraj Vladika, Daniel Braun, Florian Matthes
2023 J jnl
Challenges in Domain-Specific Abstractive Summarization and How to Overcome them.
CoRR
Anum Afzal, Juraj Vladika, Daniel Braun, Florian Matthes
2023 J jnl
Investigating Conversational Search Behavior For Domain Exploration.
CoRR
Phillip Schneider, Anum Afzal, Juraj Vladika, Daniel Braun, Florian Matthes
2023 — conf
Investigating Conversational Search Behavior for Domain Exploration.
ECIR (2)
Phillip Schneider, Anum Afzal, Juraj Vladika, Daniel Braun, Florian Matthes