Papers by Maria Teleki
Quantifying the Impact of Disfluency on Spoken Content Summarization (2024.lrec-main)
Copied to clipboard
| Challenge: | a recent study has found that disfluencies negatively impact spoken content summarization . |
| Approach: | They aim to quantify the impact of disfluency on spoken content summarization . they also investigate two methods towards improving summarizing in the presence of disflouencies . |
| Outcome: | The proposed methods improve summarization quality in the presence of disfluencies. |
A Survey on LLMs for Story Generation (2025.findings-emnlp)
Copied to clipboard
Maria Teleki, Vedangi Bengali, Xiangjue Dong, Sai Tejas Janjur, Haoran Liu, Tian Liu, Cong Wang, Ting Liu, Yin Zhang, Frank Shipman, James Caverlee
| Challenge: | Methods for story generation with Large Language Models (LLMs) have come into the spotlight recently. |
| Approach: | They propose a novel taxonomy of LLMs for story generation consisting of two major paradigms: independent story generation by an LLM, and author-assistance for story creation . |
| Outcome: | The proposed taxonomy compares existing work on the topic with those of novel author-assistance models. |
DACL: Disfluency Augmented Curriculum Learning for Fluent Text Generation (2024.lrec-main)
Copied to clipboard
| Challenge: | Disfluency-aware language models are traditionally trained on fluent, written text corpora. |
| Approach: | They propose a Disfluency Augmented Curriculum Learning approach to tackle disfluency . they use CL coupled with synthetically augmented disfluent texts of various levels . |
| Outcome: | The proposed model surpasses existing techniques in word-based precision (by up to 1%) and has shown favorable recall and F1 scores. |
Co2PT: Mitigating Bias in Pre-trained Language Models through Counterfactual Contrastive Prompt Tuning (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Pre-trained language models can encode unfair social biases from large pre-training corpora and even amplify biase in downstream applications. |
| Approach: | They propose a *debias-while-prompt tuning* method for mitigating biases via counterfactual contrastive prompt tuning on downstream tasks. |
| Outcome: | The proposed method can mitigate biases on three extrinsic bias benchmarks and adapt to existing debiased language models. |
CHOIR: Harmonizing Structured Persona Diversity for Robust Collaborative LLM Reasoning (2026.acl-long)
Copied to clipboard
| Challenge: | Persona-assigned Large Language Models can be useful for personalized, context-aware reasoning. |
| Approach: | They propose a framework that harmonizes demographic perturbations into a unified prediction by balancing agreement and divergence among counterfactual personas. |
| Outcome: | The proposed framework improves reasoning performance even when base personas are suboptimal. |