There exists a discrepancy between the token-level objective during training and the overall sequence-level quality that is expected from the model. This discrepancy leads to issues like exposure bias.To align the model with human expectations, sequence-level objectives are often used to fine-tune pre-trained models.In this paper, we introduce a contrastive preference model that enhances the traditional Plackett-Luce model by incorporating an indicator function. Building upon this novel preference model, we propose Contrastive Preference Learning (CPL), which uses offline samples with list-wise preferences to fine-tune a pre-trained model in Neural Machine Translation. Our experiments, conducted on three language pairs, demonstrate that CPL outperforms not only the vanilla Transformer model but also other token-level and sequence-level baselines. Furthermore, the ablation study highlights the essential role of the proposed indicator function in achieving this improvement.

Large language models (LLMs) have demonstrated the capacity to improve summary quality by mirroring a human-like iterative process of critique and refinement starting from the initial draft. Two strategies are designed to perform this iterative process: Prompt Chaining and Stepwise Prompt. Prompt chaining orchestrates the drafting, critiquing, and refining phases through a series of three discrete prompts, while Stepwise prompt integrates these phases within a single prompt. However, the relative effectiveness of the two methods has not been extensively studied. This paper is dedicated to examining and comparing these two methods in the context of text summarization to ascertain which method stands out as the most effective. Experimental results show that the prompt chaining method can produce a more favorable outcome. This might be because stepwise prompt might produce a simulated refinement process according to our various experiments. Since refinement is adaptable to diverse tasks, our conclusions have the potential to be extrapolated to other applications, thereby offering insights that may contribute to the broader development of LLMs.

Critique, as a natural language description for assessing the quality of model-generated content, has played a vital role in the training, evaluation, and refinement of LLMs. However, a systematic method to evaluate the quality of critique is lacking. In this paper, we pioneer the critique of critique, termed MetaCritique, which builds specific quantification criteria. To achieve a reliable evaluation outcome, we propose Atomic Information Units (AIUs), which describe the critique in a more fine-grained manner. MetaCritique aggregates each AIU’s judgment for the overall score. Moreover, MetaCritique delivers a natural language rationale for the intricate reasoning within each judgment. Lastly, we construct a meta-evaluation dataset covering 4 tasks across 16 public datasets involving human-written and LLM-generated critiques. Experiments demonstrate that MetaCritique can achieve near-human performance. Our study can facilitate future research in LLM critiques based on our following observations and released resources: (1) superior critiques judged by MetaCritique can lead to better refinements, indicating that it can potentially enhance the alignment of existing LLMs; (2) the leaderboard of critique models reveals that open-source critique models commonly suffer from factuality issues; (3) relevant code and data are publicly available at https://anonymous.4open.science/r/MetaCritique-ARR/ to support deeper exploration; (4) an API at PyPI with the usage documentation in Appendix C allows users to assess the critique conveniently.

As a relative quality comparison of model responses, human and Large Language Model (LLM) preferences serve as common alignment goals in model fine-tuning and criteria in evaluation. Yet, these preferences merely reflect broad tendencies, resulting in less explainable and controllable models with potential safety risks. In this work, we dissect the preferences of human and 32 different LLMs to understand their quantitative composition, using annotations from real-world user-model conversations for a fine-grained, scenario-wise analysis. We find that humans are less sensitive to errors, favor responses that support their stances, and show clear dislike when models admit their limits. On the contrary, advanced LLMs like GPT-4-Turbo emphasize correctness, clarity, and harmlessness more. Additionally, LLMs of similar sizes tend to exhibit similar preferences, regardless of their training methods, and fine-tuning for alignment does not significantly alter the preferences of pretrained-only LLMs. Finally, we show that preference-based evaluation can be intentionally manipulated. In both training-free and training-based settings, aligning a model with the preferences of judges boosts scores, while injecting the least preferred properties lowers them. This results in notable score shifts: up to 0.59 on MT-Bench (1-10 scale) and 31.94 on AlpacaEval 2.0 (0-100 scale), highlighting the significant impact of this strategic adaptation. We have made all resources of this project publicly available.

Extractive summarization aims to select a set of salient sentences from the source document to form a summary. Context information has been considered one of the key factors for this task. Meanwhile, there also exist other pattern factors that can identify sentence importance, such as sentence position or certain n-gram tokens. However, such pattern information is only effective in specific datasets or domains and can not be generalized like the context information when there only exists limited data. In this case, current extractive summarization models may suffer from a performance drop when transferring to a new dataset. In this paper, we attempt to apply disentangled representation learning on extractive summarization, and separate the two key factors for the task, context and pattern, for a better generalization ability in the low-resource setting. To achieve this, we propose two groups of losses for encoding and disentangling sentence representations into context representations and pattern representations. In this case, we can either use only the context information in the zero-shot setting or fine-tune the pattern information in the few-shot setting. Experimental results on three summarization datasets from different domains show the effectiveness of our proposed approach.

Abstractive Text Summarization (ATS) models are commonly trained using large-scale data that is randomly shuffled. However, the impact of data selection and data ordering on ATS models remains a relatively unexplored research area, where a significant challenge lies in accurately assessing the learning difficulty of each training instance. This study introduces a Data Selection Curriculum (DSC) scoring system that incorporates both the difficulty of improving ATS model via an instance and the expected performance on this instance. By selectively excluding excessively simple and overly complex instances, the training efficiency can be optimized. Furthermore, curriculum learning is integrated to accelerate convergence and improve performance by gradually increasing the learning difficulty, inspired by human learners. Experimental results on the CNN/DailyMail dataset demonstrate that our approach surpasses potent baselines, utilizing a mere 20% of the available instances.

Beam search is the most popular decoding method for Neural Machine Translation (NMT) and is still a strong baseline compared with the newly proposed sampling-based methods. To better understand beam search, we investigate its two well-recognized issues, beam search curse and search errors, at the sentence level. We find that only less than 30% of sentences in the test set experience these issues. Meanwhile, there is a related phenomenon. For the majority of sentences, their gold references have lower probabilities than the predictions from beam search. We also test with different levels of model errors including a special test using training samples and models without regularization. We find that these phenomena still exist even for a model with an accuracy of 95% although they are mitigated. These findings show that it is not promising to improve beam search by seeking higher probabilities in searching and further reducing its search errors. The relationship between the quality and the probability of predictions at the sentence level in our results provides useful information to find new ways to improve NMT.