paper-with-me

홈 › Papers

Taming LLMs with Negative Samples: A Reference-Free Framework to Evaluate Presentation Content with Actionable Feedback

2025-05-23 · Ananth Muppidi, Tarak Das, Sambaran Bandyopadhyay, Tripti Shukla, Dharun D A

The generation of presentation slides automatically is an important problem in the era of generative AI. This paper focuses on evaluating multimodal content in presentation slides that can effectively summarize a document and convey concepts to a broad audience. We introduce a benchmark dataset, RefSlides, consisting of human-made high-quality presentations that span various topics. Next, we propose a set of metrics to characterize different intrinsic properties of the content of a presentation and present REFLEX, an evaluation approach that generates scores and actionable feedback for these metrics. We achieve this by generating negative presentation samples with different degrees of metric-specific perturbations and use them to fine-tune LLMs. This reference-free evaluation technique does not require ground truth presentations during inference. Our extensive automated and human experiments demonstrate that our evaluation approach outperforms classical heuristic-based and state-of-the-art large language model-based evaluations in generating scores and explanations.

📄 PDF Abstract BibTeX arXiv:2505.18240

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingLarge Language Model

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Negating Negatives: Alignment with Human Negative Samples via Distributional Dispreference Optimization

2024-03-06 · Shitong Duan, Xiaoyuan Yi, Peng Zhang, Yan Liu 외

Large language models (LLMs) have revolutionized the role of AI, yet pose potential social risks. To steer LLMs towards human preference, alignment technologies have been introduced and gained increasing attention. Never…

Distributional Preference Alignment of LLMs via Optimal Transport

2024-06-09 · Igor Melnyk, Youssef Mroueh, Brian Belgodere, Mattia Rigotti 외

Current LLM alignment techniques use pairwise human preferences at a sample level, and as such, they do not imply an alignment on the distributional level. We propose in this paper Alignment via Optimal Transport (AOT), …

On Negative-aware Preference Optimization for Recommendation

2025-08-13 · Chenlu Ding, Daoxuan Liu, Jiancan Wu, Xingyu Hu 외 arxiv

Recommendation systems leverage user interaction data to suggest relevant items while filtering out irrelevant (negative) ones. The rise of large language models (LLMs) has garnered increasing attention for their potenti…

Recommendation Systems

Taming Recommendation Bias with Causal Intervention on Evolving Personal Popularity

2025-05-20 · Shiyin Tan, Dongyuan Li, Renhe Jiang, Zhen Wang 외

Popularity bias occurs when popular items are recommended far more frequently than they should be, negatively impacting both user experience and recommendation accuracy. Existing debiasing methods mitigate popularity bia…

SeaPO: Strategic Error Amplification for Robust Preference Optimization of Large Language Models

2025-09-29 · Jun Rao, Yunjie Liao, Xuebo Liu, Zepeng Lin 외 arxiv

Existing alignment methods for preference optimization of large language models (LLMs) aim to enhance model performance by utilizing pairs of positive and negative samples. However, due to the limited capacity of models …