Improving LLM-based Machine Translation with Systematic Self-Correction

Large Language Models (LLMs) have achieved impressive results in Machine Translation (MT). However, careful evaluations by human reveal that the translations produced by LLMs still contain multiple errors. Importantly, feeding back such error information into the LLMs can lead to self-correction and result in improved translation performance. Motivated by these insights, we introduce a systematic LLM-based self-correcting translation framework, named TER, which stands for Translate, Estimate, and Refine, marking a significant step forward in this direction. Our findings demonstrate that 1) our self-correction framework successfully assists LLMs in improving their translation quality across a wide range of languages, whether it's from high-resource languages to low-resource ones or whether it's English-centric or centered around other languages; 2) TER exhibits superior systematicity and interpretability compared to previous methods; 3) different estimation strategies yield varied impacts on AI feedback, directly affecting the effectiveness of the final corrections. We further compare different LLMs and conduct various experiments involving self-correction and cross-model correction to investigate the potential relationship between the translation and evaluation capabilities of LLMs. Our code and data are available at https://github.com/fzp0424/self_correct_mt

Divide and Conquer for Large Language Models Reasoning

Large language models (LLMs) have shown impressive performance in various reasoning benchmarks with the emergence of Chain-of-Thought (CoT) and its derivative methods, particularly in tasks involving multi-choice questions (MCQs). However, current works all process data uniformly without considering the problem-solving difficulty, which means an excessive focus on simple questions while insufficient to intricate ones. To address this challenge, we inspired by humans using heuristic strategies to categorize tasks and handle them individually, propose to apply the Divide and Conquer to LLMs reasoning. First, we divide questions into different subsets based on the statistical confidence score ($\mathcal{CS}$), then fix nearly resolved sets and conquer demanding nuanced process ones with elaborately designed methods, including Prior Knowledge based Reasoning (PKR) and Filter Choices based Reasoning (FCR), as well as their integration variants. Our experiments demonstrate that this proposed strategy significantly boosts the models' reasoning abilities across nine datasets involving arithmetic, commonsense, and logic tasks. For instance, compared to baseline, we make a striking improvement on low confidence subsets of 8.72\% for AQuA, 15.07\% for ARC Challenge and 7.71\% for RiddleSense. In addition, through extensive analysis on length of rationale and number of options, we verify that longer reasoning paths in PKR could prevent models from referring infer-harmful shortcuts, and also find that removing irrelevant choices in FCR would substantially avoid models' confusion. The code is at \url{https://github.com/AiMijie/Divide-and-Conquer}

How Well Do Text Embedding Models Understand Syntax?

Text embedding models have significantly contributed to advancements in natural language processing by adeptly capturing semantic properties of textual data. However, the ability of these models to generalize across a wide range of syntactic contexts remains under-explored. In this paper, we first develop an evaluation set, named \textbf{SR}, to scrutinize the capability for syntax understanding of text embedding models from two crucial syntactic aspects: Structural heuristics, and Relational understanding among concepts, as revealed by the performance gaps in previous studies. Our findings reveal that existing text embedding models have not sufficiently addressed these syntactic understanding challenges, and such ineffectiveness becomes even more apparent when evaluated against existing benchmark datasets. Furthermore, we conduct rigorous analysis to unearth factors that lead to such limitations and examine why previous evaluations fail to detect such ineffectiveness. Lastly, we propose strategies to augment the generalization ability of text embedding models in diverse syntactic scenarios. This study serves to highlight the hurdles associated with syntactic generalization and provides pragmatic guidance for boosting model performance across varied syntactic contexts.

Learning from Mixed Datasets: A Monotonic Image Quality Assessment Model

Deep learning based image quality assessment (IQA) models usually learn to predict image quality from a single dataset, leading the model to overfit specific scenes. To account for this, mixed datasets training can be an effective way to enhance the generalization capability of the model. However, it is nontrivial to combine different IQA datasets, as their quality evaluation criteria, score ranges, view conditions, as well as subjects are usually not shared during the image quality annotation. In this paper, instead of aligning the annotations, we propose a monotonic neural network for IQA model learning with different datasets combined. In particular, our model consists of a dataset-shared quality regressor and several dataset-specific quality transformers. The quality regressor aims to obtain the perceptual qualities of each dataset while each quality transformer maps the perceptual qualities to the corresponding dataset annotations with their monotonicity maintained. The experimental results verify the effectiveness of the proposed learning strategy and our code is available at https://github.com/fzp0424/MonotonicIQA.