Related papers: PePe: Personalized Post-editing Model utilizing Us…
Even the most advanced language models remain susceptible to errors necessitating to modify these models without initiating a comprehensive retraining process. Model editing refers to the modification of a model's knowledge or…
Personalization is central to human-AI interaction, yet current diffusion-based image generation systems remain largely insensitive to user diversity. Existing attempts to address this often rely on costly paired preference data or…
Personalized opinion summarization is crucial as it considers individual user interests while generating product summaries. Recent studies show that although large language models demonstrate powerful text summarization and evaluation…
Modern NLP defines the task of style transfer as modifying the style of a given sentence without appreciably changing its semantics, which implies that the outputs of style transfer systems should be paraphrases of their inputs. However,…
Recommendation systems play a pivotal role in suggesting items to users based on their preferences. However, in online platforms, these systems inevitably offer unsuitable recommendations due to limited model capacity, poor data quality, or…
Professional-grade software applications are powerful but complicated$-$expert users can achieve impressive results, but novices often struggle to complete even basic tasks. Photo editing is a prime example: after loading a photo, the user…
Personalized large language models (LLMs) tailor content to individual preferences using user profiles or histories. However, existing parameter-efficient fine-tuning (PEFT) methods, such as the ``One-PEFT-Per-User'' (OPPU) paradigm,…
We study private synthetic data generation for query release, where the goal is to construct a sanitized version of a sensitive dataset, subject to differential privacy, that approximately preserves the answers to a large collection of…
In this work, we explore multiple neural architectures adapted for the task of automatic post-editing of machine translation output. We focus on neural end-to-end models that combine both inputs $mt$ (raw MT output) and $src$ (source…
Iterative data generation and model re-training can effectively align large language models(LLMs) to human preferences. The process of data sampling is crucial, as it significantly influences the success of policy improvement. Repeated…
This paper introduces Meta-PerSER, a novel meta-learning framework that personalizes Speech Emotion Recognition (SER) by adapting to each listener's unique way of interpreting emotion. Conventional SER systems rely on aggregated…
Evaluating AI systems that interact with humans requires understanding their behavior across diverse user populations, but collecting representative human data is often expensive or infeasible, particularly for novel technologies or…
Personalized text-to-image generation aims to create images tailored to user-defined concepts and textual descriptions. Balancing the fidelity of the learned concept with its ability for generation in various contexts presents a significant…
Grounded dialogue models generate responses that are grounded on certain concepts. Limited by the distribution of grounded dialogue data, models trained on such data face the transferability challenges in terms of the data distribution and…
Common image editing tasks typically adopt powerful generative diffusion models as the leading paradigm for real-world content editing. Meanwhile, although reinforcement learning (RL) methods such as Diffusion-DPO and Flow-GRPO have further…
Like humans, large language models (LLMs) do not always generate the best output on their first try. Motivated by how humans refine their written text, we introduce Self-Refine, an approach for improving initial outputs from LLMs through…
Offensive and abusive language is a pressing problem on social media platforms. In this work, we propose a method for transforming offensive comments, statements containing profanity or offensive language, into non-offensive ones. We design…
The advantages of neural machine translation (NMT) have been extensively validated for offline translation of several language pairs for different domains of spoken and written language. However, research on interactive learning of NMT by…
Existing approaches to recipe generation are unable to create recipes for users with culinary preferences but incomplete knowledge of ingredients in specific dishes. We propose a new task of personalized recipe generation to help these…
Human ratings are one of the most prevalent methods to evaluate the performance of natural language processing algorithms. Similarly, it is common to measure the quality of sentences generated by a natural language generation model using…