Large language models (LLMs) have shown promise as automated evaluators for assessing the quality of answers generated by AI systems. However, LLM-based evaluators exhibit position bias, or inconsistency, when used to evaluate candidate answers in pairwise comparisons, favoring either the first or second answer regardless of content. To address this limitation, we propose PORTIA, an alignment-based system designed to mimic human comparison strategies to calibrate position bias in a lightweight yet effective manner. Specifically, PORTIA splits the answers into multiple segments, taking into account both length and semantics, and merges them back into a single prompt for evaluation by LLMs. Extensive experiments with six LLMs on 11,520 answer pairs demonstrate that PORTIA markedly enhances the consistency rates for all models and forms of comparison tested, achieving an average relative improvement of 47.46%. It also enables PORTIA-enhanced GPT-3.5 to achieve agreement rates with humans comparable to GPT-4 and elevates GPT-4’s consistency rate up to 98%. Subsequent human evaluations indicate that the PORTIA-enhanced GPT-3.5 model can even surpass standalone GPT-4 in terms of alignment with human evaluators, highlighting PORTIA’s ability to correct position bias, improve LLM consistency, and boost performance while keeping cost efficiency.

Large Language Model (LLM)-based approach has become the mainstream for Text-to-SQL task and achieves remarkable performance. In this paper, we augment the existing prompt engineering methods by exploiting the database content and execution feedback. Specifically, we introduce DART-SQL, which comprises two key components: (1) Question Rewriting: DART-SQL rewrites natural language questions by leveraging database content information to eliminate ambiguity. (2) Execution-Guided Refinement: DART-SQL incorporates database content information and utilizes the execution results of the generated SQL to iteratively refine the SQL. We apply this framework to the two LLM-based approaches (DAIL-SQL and C3) and test it on four widely used benchmarks (Spider-dev, Spider-test, Realistic and DK). Experiments show that our framework for DAIL-SQL and C3 achieves an average improvement of 12.41% and 5.38%, respectively, in terms of execution accuracy(EX) metric.

Sparse models, including sparse Mixture-of-Experts (MoE) models, have emerged as an effective approach for scaling Transformer models. However, they often suffer from computational inefficiency since a significant number of parameters are unnecessarily involved in computations by multiplying values by zero or low activation values. To address this issue, we present XMoE, a novel MoE designed to enhance both the efficacy and efficiency of sparse MoE models. XMoE leverages small experts and a threshold-based router to enable tokens to selectively engage only essential parameters. Our extensive experiments on language modeling and machine translation tasks demonstrate that enhances model performance and can decrease the computation load at MoE layers by over 50% without sacrificing performance. Furthermore, we present the versatility of by applying it to dense models, enabling sparse computation during inference. We provide a comprehensive analysis and make our code available at https://anonymous.4open.science/r/XMoE.

Natural language processing for programming aims to use NLP techniques to assist programming. It is increasingly prevalent for its effectiveness in improving productivity. Distinct from natural language, a programming language is highly structured and functional. Constructing a structure-based representation and a functionality-oriented algorithm is at the heart of program understanding and generation. In this paper, we conduct a systematic review covering tasks, datasets, evaluation methods, techniques, and models from the perspective of the structure-based and functionality-oriented property, aiming to understand the role of the two properties in each component. Based on the analysis, we illustrate unexplored areas and suggest potential directions for future work.

Transformer-based models have achieved great success on sentence pair modeling tasks, such as answer selection and natural language inference (NLI). These models generally perform cross-attention over input pairs, leading to prohibitive computational cost. Recent studies propose dual-encoder and late interaction architectures for faster computation. However, the balance between the expressive of cross-attention and computation speedup still needs better coordinated. To this end, this paper introduces a novel paradigm TopicAns for efficient sentence pair modeling. TopicAns involves a lightweight cross-attention mechanism. It conducts query encoding only once while modeling the query-candidate interaction in parallel. Extensive experiments conducted on four tasks demonstrate that our TopicAnscan speed up sentence pairing by over 113x while achieving comparable performance as the more expensive cross-attention models.

Aspect-based sentiment analysis aims to identify sentiment polarity of social media users toward different aspects. Most recent methods adopt the aspect-centric latent tree to connect aspects and their corresponding opinion words, thinking that would facilitate establishing the relationship between aspects and opinion words.However, these methods ignore the roles of syntax dependency relation labels and affective semantic information in determining the sentiment polarity, resulting in the wrong prediction.In this paper, we propose a novel multi-graph fusion network (MGFN) based on latent graph to leverage the richer syntax dependency relation label information and affective semantic information of words.Specifically, we construct a novel syntax-aware latent graph (SaLG) to fully leverage the syntax dependency relation label information to facilitate the learning of sentiment representations. Subsequently, a multi-graph fusion module is proposed to fuse semantic information of surrounding contexts of aspects adaptively. Furthermore, we design an affective refinement strategy to guide the MGFN to capture significant affective clues. Extensive experiments on three datasets demonstrate that our MGFN model outperforms all state-of-the-art methods and verify the effectiveness of our model.

This paper presents an unsupervised framework for jointly modeling topic content and discourse behavior in microblog conversations. Concretely, we propose a neural model to discover word clusters indicating what a conversation concerns (i.e., topics) and those reflecting how participants voice their opinions (i.e., discourse).1 Extensive experiments show that our model can yield both coherent topics and meaningful discourse behavior. Further study shows that our topic and discourse representations can benefit the classification of microblog messages, especially when they are jointly trained with the classifier. Our data sets and code are available at: http://github.com/zengjichuan/Topic_Disc.

Many classification models work poorly on short texts due to data sparsity. To address this issue, we propose topic memory networks for short text classification with a novel topic memory mechanism to encode latent topic representations indicative of class labels. Different from most prior work that focuses on extending features with external knowledge or pre-trained topics, our model jointly explores topic inference and text classification with memory networks in an end-to-end manner. Experimental results on four benchmark datasets show that our model outperforms state-of-the-art models on short text classification, meanwhile generates coherent topics.