Investigating Context-Faithfulness in Large Language Models: The Roles of Memory Strength and Evidence Style

Retrieval-augmented generation (RAG) improves Large Language Models (LLMs) by incorporating external information into the response generation process. However, how context-faithful LLMs are and what factors influence LLMs' context-faithfulness remain largely unexplored. In this study, we investigate the impact of memory strength and evidence presentation on LLMs' receptiveness to external evidence. We introduce a method to quantify the memory strength of LLMs by measuring the divergence in LLMs' responses to different paraphrases of the same question, which is not considered by previous works. We also generate evidence in various styles to evaluate the effects of evidence in different styles. Two datasets are used for evaluation: Natural Questions (NQ) with popular questions and popQA featuring long-tail questions. Our results show that for questions with high memory strength, LLMs are more likely to rely on internal memory, particularly for larger LLMs such as GPT-4. On the other hand, presenting paraphrased evidence significantly increases LLMs' receptiveness compared to simple repetition or adding details.

Re-Examine Distantly Supervised NER: A New Benchmark and a Simple Approach

This paper delves into Named Entity Recognition (NER) under the framework of Distant Supervision (DS-NER), where the main challenge lies in the compromised quality of labels due to inherent errors such as false positives, false negatives, and positive type errors. We critically assess the efficacy of current DS-NER methodologies using a real-world benchmark dataset named QTL, revealing that their performance often does not meet expectations. To tackle the prevalent issue of label noise, we introduce a simple yet effective approach, Curriculum-based Positive-Unlabeled Learning CuPUL, which strategically starts on "easy" and cleaner samples during the training process to enhance model resilience to noisy samples. Our empirical results highlight the capability of CuPUL to significantly reduce the impact of noisy labels and outperform existing methods. QTL dataset and our code is available on GitHub.

Training-free image style alignment for self-adapting domain shift on handheld ultrasound devices

Handheld ultrasound devices face usage limitations due to user inexperience and cannot benefit from supervised deep learning without extensive expert annotations. Moreover, the models trained on standard ultrasound device data are constrained by training data distribution and perform poorly when directly applied to handheld device data. In this study, we propose the Training-free Image Style Alignment (TISA) framework to align the style of handheld device data to those of standard devices. The proposed TISA can directly infer handheld device images without extra training and is suited for clinical applications. We show that TISA performs better and more stably in medical detection and segmentation tasks for handheld device data. We further validate TISA as the clinical model for automatic measurements of spinal curvature and carotid intima-media thickness. The automatic measurements agree well with manual measurements made by human experts and the measurement errors remain within clinically acceptable ranges. We demonstrate the potential for TISA to facilitate automatic diagnosis on handheld ultrasound devices and expedite their eventual widespread use.

Improving Unsupervised Relation Extraction by Augmenting Diverse Sentence Pairs

Unsupervised relation extraction (URE) aims to extract relations between named entities from raw text without requiring manual annotations or pre-existing knowledge bases. In recent studies of URE, researchers put a notable emphasis on contrastive learning strategies for acquiring relation representations. However, these studies often overlook two important aspects: the inclusion of diverse positive pairs for contrastive learning and the exploration of appropriate loss functions. In this paper, we propose AugURE with both within-sentence pairs augmentation and augmentation through cross-sentence pairs extraction to increase the diversity of positive pairs and strengthen the discriminative power of contrastive learning. We also identify the limitation of noise-contrastive estimation (NCE) loss for relation representation learning and propose to apply margin loss for sentence pairs. Experiments on NYT-FB and TACRED datasets demonstrate that the proposed relation representation learning and a simple K-Means clustering achieves state-of-the-art performance.

LLMRec: Benchmarking Large Language Models on Recommendation Task

Recently, the fast development of Large Language Models (LLMs) such as ChatGPT has significantly advanced NLP tasks by enhancing the capabilities of conversational models. However, the application of LLMs in the recommendation domain has not been thoroughly investigated. To bridge this gap, we propose LLMRec, a LLM-based recommender system designed for benchmarking LLMs on various recommendation tasks. Specifically, we benchmark several popular off-the-shelf LLMs, such as ChatGPT, LLaMA, ChatGLM, on five recommendation tasks, including rating prediction, sequential recommendation, direct recommendation, explanation generation, and review summarization. Furthermore, we investigate the effectiveness of supervised finetuning to improve LLMs' instruction compliance ability. The benchmark results indicate that LLMs displayed only moderate proficiency in accuracy-based tasks such as sequential and direct recommendation. However, they demonstrated comparable performance to state-of-the-art methods in explainability-based tasks. We also conduct qualitative evaluations to further evaluate the quality of contents generated by different models, and the results show that LLMs can truly understand the provided information and generate clearer and more reasonable results. We aspire that this benchmark will serve as an inspiration for researchers to delve deeper into the potential of LLMs in enhancing recommendation performance. Our codes, processed data and benchmark results are available at https://github.com/williamliujl/LLMRec.

Relation-Aware Network with Attention-Based Loss for Few-Shot Knowledge Graph Completion

Few-shot knowledge graph completion (FKGC) task aims to predict unseen facts of a relation with few-shot reference entity pairs. Current approaches randomly select one negative sample for each reference entity pair to minimize a margin-based ranking loss, which easily leads to a zero-loss problem if the negative sample is far away from the positive sample and then out of the margin. Moreover, the entity should have a different representation under a different context. To tackle these issues, we propose a novel Relation-Aware Network with Attention-Based Loss (RANA) framework. Specifically, to better utilize the plentiful negative samples and alleviate the zero-loss issue, we strategically select relevant negative samples and design an attention-based loss function to further differentiate the importance of each negative sample. The intuition is that negative samples more similar to positive samples will contribute more to the model. Further, we design a dynamic relation-aware entity encoder for learning a context-dependent entity representation. Experiments demonstrate that RANA outperforms the state-of-the-art models on two benchmark datasets.

Is ChatGPT a Good Recommender? A Preliminary Study

Recommendation systems have witnessed significant advancements and have been widely used over the past decades. However, most traditional recommendation methods are task-specific and therefore lack efficient generalization ability. Recently, the emergence of ChatGPT has significantly advanced NLP tasks by enhancing the capabilities of conversational models. Nonetheless, the application of ChatGPT in the recommendation domain has not been thoroughly investigated. In this paper, we employ ChatGPT as a general-purpose recommendation model to explore its potential for transferring extensive linguistic and world knowledge acquired from large-scale corpora to recommendation scenarios. Specifically, we design a set of prompts and evaluate ChatGPT's performance on five recommendation scenarios. Unlike traditional recommendation methods, we do not fine-tune ChatGPT during the entire evaluation process, relying only on the prompts themselves to convert recommendation tasks into natural language tasks. Further, we explore the use of few-shot prompting to inject interaction information that contains user potential interest to help ChatGPT better understand user needs and interests. Comprehensive experimental results on Amazon Beauty dataset show that ChatGPT has achieved promising results in certain tasks and is capable of reaching the baseline level in others. We conduct human evaluations on two explainability-oriented tasks to more accurately evaluate the quality of contents generated by different models. And the human evaluations show ChatGPT can truly understand the provided information and generate clearer and more reasonable results. We hope that our study can inspire researchers to further explore the potential of language models like ChatGPT to improve recommendation performance and contribute to the advancement of the recommendation systems field.

Improving Distantly Supervised Relation Extraction by Natural Language Inference

To reduce human annotations for relation extraction (RE) tasks, distantly supervised approaches have been proposed, while struggling with low performance. In this work, we propose a novel DSRE-NLI framework, which considers both distant supervision from existing knowledge bases and indirect supervision from pretrained language models for other tasks. DSRE-NLI energizes an off-the-shelf natural language inference (NLI) engine with a semi-automatic relation verbalization (SARV) mechanism to provide indirect supervision and further consolidates the distant annotations to benefit multi-classification RE models. The NLI-based indirect supervision acquires only one relation verbalization template from humans as a semantically general template for each relationship, and then the template set is enriched by high-quality textual patterns automatically mined from the distantly annotated corpus. With two simple and effective data consolidation strategies, the quality of training data is substantially improved. Extensive experiments demonstrate that the proposed framework significantly improves the SOTA performance (up to 7.73\% of F1) on distantly supervised RE benchmark datasets.

Proxy-bridged Image Reconstruction Network for Anomaly Detection in Medical Images

Anomaly detection in medical images refers to the identification of abnormal images with only normal images in the training set. Most existing methods solve this problem with a self-reconstruction framework, which tends to learn an identity mapping and reduces the sensitivity to anomalies. To mitigate this problem, in this paper, we propose a novel Proxy-bridged Image Reconstruction Network (ProxyAno) for anomaly detection in medical images. Specifically, we use an intermediate proxy to bridge the input image and the reconstructed image. We study different proxy types, and we find that the superpixel-image (SI) is the best one. We set all pixels' intensities within each superpixel as their average intensity, and denote this image as SI. The proposed ProxyAno consists of two modules, a Proxy Extraction Module and an Image Reconstruction Module. In the Proxy Extraction Module, a memory is introduced to memorize the feature correspondence for normal image to its corresponding SI, while the memorized correspondence does not apply to the abnormal images, which leads to the information loss for abnormal image and facilitates the anomaly detection. In the Image Reconstruction Module, we map an SI to its reconstructed image. Further, we crop a patch from the image and paste it on the normal SI to mimic the anomalies, and enforce the network to reconstruct the normal image even with the pseudo abnormal SI. In this way, our network enlarges the reconstruction error for anomalies. Extensive experiments on brain MR images, retinal OCT images and retinal fundus images verify the effectiveness of our method for both image-level and pixel-level anomaly detection.

Automatic segmentation of vertebral features on ultrasound spine images using Stacked Hourglass Network

Objective: The spinous process angle (SPA) is one of the essential parameters to denote three-dimensional (3-D) deformity of spine. We propose an automatic segmentation method based on Stacked Hourglass Network (SHN) to detect the spinous processes (SP) on ultrasound (US) spine images and to measure the SPAs of clinical scoliotic subjects. Methods: The network was trained to detect vertebral SP and laminae as five landmarks on 1200 ultrasound transverse images and validated on 100 images. All the processed transverse images with highlighted SP and laminae were reconstructed into a 3D image volume, and the SPAs were measured on the projected coronal images. The trained network was tested on 400 images by calculating the percentage of correct keypoints (PCK); and the SPA measurements were evaluated on 50 scoliotic subjects by comparing the results from US images and radiographs. Results: The trained network achieved a high average PCK (86.8%) on the test datasets, particularly the PCK of SP detection was 90.3%. The SPAs measured from US and radiographic methods showed good correlation (r>0.85), and the mean absolute differences (MAD) between two modalities were 3.3{\deg}, which was less than the clinical acceptance error (5{\deg}). Conclusion: The vertebral features can be accurately segmented on US spine images using SHN, and the measurement results of SPA from US data was comparable to the gold standard from radiography.