Papers by Christèle Tarnec
PoSum-Bench: Benchmarking Position Bias in LLM-based Conversational Summarization (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large language models exhibit positional bias, a problem that can undermine the completeness of conversation summarizations. |
| Approach: | They propose a semantic similarity-based sentence-level metric to quantify positional bias in conversational summaries. |
| Outcome: | The proposed benchmark provides the first systematic evaluation of positional bias in conversational summarization across languages and contexts. |