Recently, large language models (LLMs) have demonstrated breakthrough mathematical problem-solving capabilities in grade school math word problems (MWP). For example, on the MWP benchmark GSM8K, the accuracy of GPT-3.5-Turbo and MetaMath-70B reaches 80.80% and 82.30%, respectively. One question arises, does it mean that LLMs have truly mastered related mathematical problem-solving abilities? In this paper, by presenting two types of benchmarks, where MCGSM8K aims at selecting one correct solution from four solutions, while GSM8K-Judgement judges whether a solution to a given question is true or false, we demonstrate that the ability of most LLMs to evaluate the mathematical reasoning process of MWP is far from sufficient. To compensate for this issue, we propose hybrid supervised fine-tuning data from the training data of GSM8K, MCGSM8K, and GSM8K-Judgement, which significantly improves performance on the proposed reasoning process evaluation benchmarks. For example, fine-tuning improves the performance of LLaMA-2-13B from 33.51% to 70.89% on MCGSM8K. In conclusion, we experimentally demonstrate that most LLMs have limited ability to evaluate the mathematical reasoning process of MWP, which can be enhanced through fine-tuning.

Large language models (LLMs) with enormous pre-training tokens and parameters emerge diverse abilities, including math reasoning, codegeneration, and instruction following. These abilities are further enhanced by supervised fine-tuning (SFT). While the open-source community has explored ad-hoc SFT for enhancing individual capabilities, proprietary LLMs exhibit versatility across various skills. Therefore, understanding the facilitation of multiple abilities via SFT is paramount. In this study, we specificially focuses on the interplay of data composition between mathematical reasoning, code generation, and general human-aligning abilities during SFT. We propose four intriguing research questions to explore the association between model performance and various factors including data amount, composition ratio, model size and SFT strategies. Our experiments reveal that distinct capabilities scale differently and larger models generally show superior performance with same amount of data. Mathematical reasoning and code generation consistently improve with increasing data amount, whereas general abilities plateau after roughly a thousand samples. Moreover, we observe data composition appears to enhance various abilities under limited data conditions, yet can lead to performance conflicts when data is plentiful. Our findings also suggest the amount of composition data influences performance more than the composition ratio. In analysis of SFT strategies, we find that sequentially learning multiple skills risks catastrophic forgetting. Our proposed Dual-stage Mixed Fine-tuning (DMT) strategy offers a promising solution to learn multiple abilities with different scaling patterns.

Attribute-based Controlled Text Generation (CTG) refers to generating sentences that satisfy desirable attributes (e.g., emotions and topics). Existing work usually utilize fine-tuning or resort to extra attribute classifiers, yet suffer from increases in storage and inference time. To address these concerns, we explore attribute-based CTG in a parameter-efficient manner. In short, the proposed Tailor represents each attribute as a pre-trained continuous vector i.e., single-attribute prompt), which guides the generation of a fixed pre-trained language model (PLM) to satisfy a pre-specified attribute. These prompts can be simply concatenated as a whole for multi-attribute CTG without any re-training. Nevertheless, this may raise problems of fluency downgrading and position sensitivity. To solve this, Tailor provides two solutions to enhance the combination. The former contains a multi-attribute prompt mask and a re-indexing position sequence to bridge the gap between the training (one single-attribute prompt for each task) and the testing stage (concatenating two prompts). The latter introduces a trainable prompt connector to further enhance the combinations. Experiments demonstrate that, only requiring 0.08% extra training parameters of the GPT-2, Tailor can achieve effective and general improvements on eleven attribute-specific generation tasks.

Multi-path voting methods like Self-consistency have been used to mitigate reasoning errors in large language models caused by factual errors and illusion generation. However, these methods require excessive computing resources as they generate numerous reasoning paths for each problem. And our experiments show that on the arithmetic reasoning task, SVAMP, half of the problems fail to obtain noticeable accuracy gains when voting with more than three paths. In this paper, we propose a novel multi-path voting technique called Dynamic Voting, which effectively reduces the number of reasoning paths during multi-path voting while preserving accuracies by applying early exiting for problems that large language models can confidently solve. Experimental evaluations on arithmetic, commonsense, and symbolic reasoning tasks under few-shot and zero-shot settings demonstrate that Dynamic Voting achieves comparable accuracies employing significantly fewer reasoning paths. Notably, one of our Dynamic Voting strategies outperforms Self-consistency using only 24.7% of the number of paths on the LetterConcat task in the few-shot setting. Furthermore, Dynamic Voting showcases strong robustness in threshold selection. It also demonstrates excellent generalizability when combined with other voting techniques, different models, and diverse prompts.

Unsupervised paraphrase generation is a challenging task that benefits a variety of downstream NLP applications. Current unsupervised methods for paraphrase generation typically employ round-trip translation or denoising, which require translation corpus and result in paraphrases overly similar to the original sentences in surface structure. Most of these methods lack explicit control over the similarity between the original and generated sentences, and the entities are also less correctly kept. To obviate the reliance on translation data and prompt greater variations in surface structure, we propose a self-supervised pseudo-data construction method that generates diverse pseudo-paraphrases in distinct surface structures for a given sentence. To control the similarity and generate accurate entities, we propose an unsupervised paraphrasing model that encodes the sentence meaning and the entities with discrete and continuous variables, respectively. The similarity can be controlled by sampling discrete variables and the entities are kept substantially accurate due to the specific modeling of entities using continuous variables. Experimental results on two benchmark datasets demonstrate the advantages of our pseudo-data construction method compared to round-trip translation, and the superiority of our paraphrasing model over the state-of-the-art unsupervised methods.