Large Language Models (LLMs) have demonstrated improved generation performance by incorporating externally retrieved knowledge, a process known as retrieval-augmented generation (RAG). Despite the potential of this approach, existing studies evaluate RAG effectiveness by 1) assessing retrieval and generation components jointly, which obscures retrieval's distinct contribution, or 2) examining retrievers using traditional metrics such as NDCG, which creates a gap in understanding retrieval's true utility in the overall generation process. To address the above limitations, in this work, we introduce an automatic evaluation method that measures retrieval quality through the lens of information gain within the RAG framework. Specifically, we propose Semantic Perplexity (SePer), a metric that captures the LLM's internal belief about the correctness of the retrieved information. We quantify the utility of retrieval by the extent to which it reduces semantic perplexity post-retrieval. Extensive experiments demonstrate that SePer not only aligns closely with human preferences but also offers a more precise and efficient evaluation of retrieval utility across diverse RAG scenarios.

Retrieval module can be plugged into many downstream NLP tasks to improve their performance, such as open-domain question answering and retrieval-augmented generation. The key to a retrieval system is to calculate relevance scores to query and passage pairs. However, the definition of relevance is often ambiguous. We observed that a major class of relevance aligns with the concept of entailment in NLI tasks. Based on this observation, we designed a method called entailment tuning to improve the embedding of dense retrievers. Specifically, we unify the form of retrieval data and NLI data using existence claim as a bridge. Then, we train retrievers to predict the claims entailed in a passage with a variant task of masked prediction. Our method can be efficiently plugged into current dense retrieval methods, and experiments show the effectiveness of our method.

In this paper, an innovative multi-modal deep learning model is proposed to deeply integrate heterogeneous information from medical images and clinical reports. First, for medical images, convolutional neural networks were used to extract high-dimensional features and capture key visual information such as focal details, texture and spatial distribution. Secondly, for clinical report text, a two-way long and short-term memory network combined with an attention mechanism is used for deep semantic understanding, and key statements related to the disease are accurately captured. The two features interact and integrate effectively through the designed multi-modal fusion layer to realize the joint representation learning of image and text. In the empirical study, we selected a large medical image database covering a variety of diseases, combined with corresponding clinical reports for model training and validation. The proposed multimodal deep learning model demonstrated substantial superiority in the realms of disease classification, lesion localization, and clinical description generation, as evidenced by the experimental results.

In this paper, we employ the long-short-term memory model (LSTM) to predict the real-time go-around probability as an arrival flight is approaching JFK airport and within 10 nm of the landing runway threshold. We further develop methods to examine the causes to go-around occurrences both from a global view and an individual flight perspective. According to our results, in-trail spacing, and simultaneous runway operation appear to be the top factors that contribute to overall go-around occurrences. We then integrate these pre-trained models and analyses with real-time data streaming, and finally develop a demo web-based user interface that integrates the different components designed previously into a real-time tool that can eventually be used by flight crews and other line personnel to identify situations in which there is a high risk of a go-around.

Recently, prompt-tuning has attracted growing interests in event argument extraction (EAE). However, the existing prompt-tuning methods have not achieved satisfactory performance due to the lack of consideration of entity information. In this paper, we propose a bi-directional iterative prompt-tuning method for EAE, where the EAE task is treated as a cloze-style task to take full advantage of entity information and pre-trained language models (PLMs). Furthermore, our method explores event argument interactions by introducing the argument roles of contextual entities into prompt construction. Since template and verbalizer are two crucial components in a cloze-style prompt, we propose to utilize the role label semantic knowledge to construct a semantic verbalizer and design three kinds of templates for the EAE task. Experiments on the ACE 2005 English dataset with standard and low-resource settings show that the proposed method significantly outperforms the peer state-of-the-art methods. Our code is available at https://github.com/HustMinsLab/BIP.

A BSTRACT Neural inductive program synthesis is a task generating instructions that can produce desired outputs from given inputs. In this paper, we focus on the generation of a chunk of assembly code that can be executed to match a state change inside the CPU and RAM. We develop a neural program synthesis algorithm, AutoAssem-blet, learned via self-learning reinforcement learning that explores the large code space efficiently. Policy networks and value networks are learned to reduce the breadth and depth of the Monte Carlo Tree Search, resulting in better synthesis performance. We also propose an effective multi-entropy policy sampling technique to alleviate online update correlations. We apply AutoAssemblet to basic programming tasks and show significant higher success rates compared to several competing baselines. Much progress has been made in the field with the development of methods along the vein of neural program synthesis (Parisotto et al., 2016; Balog et al., 2017; Bunel et al., 2018; Hayati et al., 2018; Desai et al., 2016; Yin & Neubig, 2017; Kant, 2018). Neural program synthesis models build on the top of neural network architectures to synthesize human-readable programs that match desired executions.