activity
20242026
collaborators

9 papers

cs.CL2026

Low-Latency Real-Time Audio Game Commentary System via LLM-Based Parallel Text Generation

Ryota Kawamatsu, Anum Afzal, Yuki Saito +5

We present a low-latency real-time audio game commentary system that generates spoken commentary directly from live gameplay video. In this end-to-end setting, a key bottleneck is…

cs.CL2026

Real-Time Generation of Game Video Commentary with Multimodal LLMs: Pause-Aware Decoding Approaches

Anum Afzal, Yuki Saito, Hiroya Takamura +5

Real-time video commentary generation provides textual descriptions of ongoing events in videos. It supports accessibility and engagement in domains such as sports, esports, and li…

cs.CL2025

FActBench: A Benchmark for Fine-grained Automatic Evaluation of LLM-Generated Text in the Medical Domain

Anum Afzal, Juraj Vladika, Florian Matthes

Large Language Models tend to struggle when dealing with specialized domains. While all aspects of evaluation hold importance, factuality is the most critical one. Similarly, relia…

cs.CL2025

Can Smaller LLMs do better? Unlocking Cross-Domain Potential through Parameter-Efficient Fine-Tuning for Text Summarization

Anum Afzal, Mehul Kumawat, Florian Matthes

Large Language Models (LLMs), being generic task solvers, are versatile. However, despite the vast amount of data they are trained on, there are speculations about their adaptation…

cs.CL2025

Knowing Before Saying: LLM Representations Encode Information About Chain-of-Thought Success Before Completion

Anum Afzal, Florian Matthes, Gal Chechik +1

We investigate whether the success of a zero-shot Chain-of-Thought (CoT) process can be predicted before completion. We discover that a probing classifier, based on LLM representat…

cs.CL2025

JaccDiv: A Metric and Benchmark for Quantifying Diversity of Generated Marketing Text in the Music Industry

Anum Afzal, Alexandre Mercier, Florian Matthes

Online platforms are increasingly interested in using Data-to-Text technologies to generate content and help their users. Unfortunately, traditional generative methods often fall i…