Related papers: Listen, Correct, and Feed Back: Spoken Pedagogical…
Ensuring that generated utterances are faithful to dialogue actions is crucial for Task-Oriented Dialogue Response Generation. Slot Error Rate (SER) only partially measures generation quality in that it solely assesses utterances generated…
The growing need for automated and personalized feedback in programming education has led to recent interest in leveraging generative AI for feedback generation. However, current approaches tend to rely on prompt engineering techniques in…
Automated assistants for Grammatical Error Correction are now embedded in educational platforms serving millions of learners, yet three critical gaps remain in this domain: (1) latest-generation Large Language Models (LLMs) lack…
Aligning large language models (LLMs) with human preferences is essential for safe and useful LLMs. Previous works mainly adopt reinforcement learning (RLHF) and direct preference optimization (DPO) with human feedback for alignment.…
Diffusion large language models (dLLMs) are emerging as an efficient alternative to autoregressive models due to their ability to decode multiple tokens in parallel. However, aligning dLLMs with human preferences or task-specific rewards…
In this paper, we introduce Rule-Guided Feedback (RGF), a framework designed to enhance Large Language Model (LLM) performance through structured rule adherence and strategic information seeking. RGF implements a teacher-student paradigm…
Grammatical error correction (GEC) is the task of correcting typos, spelling, punctuation and grammatical issues in text. Approaching the problem as a sequence-to-sequence task, we compare the use of a common subword unit vocabulary and…
Currently available grammatical error correction (GEC) datasets are compiled using well-formed written text, limiting the applicability of these datasets to other domains such as informal writing and dialog. In this paper, we present a…
Neural sequence-to-sequence (seq2seq) approaches have proven to be successful in grammatical error correction (GEC). Based on the seq2seq framework, we propose a novel fluency boost learning and inference mechanism. Fluency boosting…
Effective personalized feedback is critical to students' literacy development. Though LLM-powered tools now promise to automate such feedback at scale, LLMs are not language-neutral: they privilege standard academic English and reproduce…
Various evaluation metrics have been proposed for Grammatical Error Correction (GEC), but many, particularly reference-free metrics, lack explainability. This lack of explainability hinders researchers from analyzing the strengths and…
Recent generative models have significantly advanced speech restoration tasks, yet their training objectives often misalign with human perceptual preferences, resulting in suboptimal quality. While post-training alignment has proven…
Generative speech enhancement offers a promising alternative to traditional discriminative methods by modeling the distribution of clean speech conditioned on noisy inputs. Post-training alignment via reinforcement learning (RL) effectively…
Self-imitating feedback is an effective and learner-friendly method for non-native learners in Computer-Assisted Pronunciation Training. Acoustic characteristics in native utterances are extracted and transplanted onto learner's own speech…
Large Multimodal Models (LMMs) have demonstrated exceptional performance across a wide range of domains. This paper explores their potential in pronunciation assessment tasks, with a particular focus on evaluating the capabilities of the…
ChatGPT,a cutting-edge AI-powered Chatbot,can quickly generate responses on given commands. While it was reported that ChatGPT had the capacity to deliver useful feedback, it is still unclear about its effectiveness compared with…
Thanks to recent advances in generative AI, we are able to prompt large language models (LLMs) to produce texts which are fluent and grammatical. In addition, it has been shown that we can elicit attempts at grammatical error correction…
In this paper, we carry out experimental research on Grammatical Error Correction, delving into the nuances of single-model systems, comparing the efficiency of ensembling and ranking methods, and exploring the application of large language…
Alignment, endowing a pre-trained Large language model (LLM) with the ability to follow instructions, is crucial for its real-world applications. Conventional supervised fine-tuning (SFT) methods formalize it as causal language modeling…
In this paper, we present strong baselines for the task of Feedback Comment Generation for Writing Learning. Given a sentence and an error span, the task is to generate a feedback comment explaining the error. Sentences and feedback…