A New Benchmark and Reverse Validation Method for Passage-level Hallucination Detection

Large Language Models (LLMs) have shown their ability to collaborate effectively with humans in real-world scenarios. However, LLMs are apt to generate hallucinations, i.e., makeup incorrect text and unverified information, which can cause significant damage when deployed for mission-critical tasks. In this paper, we propose a self-check approach based on reverse validation to detect factual errors automatically in a zero-resource fashion. To facilitate future studies and assess different methods, we construct a hallucination detection benchmark named PHD, which is generated by ChatGPT and annotated by human annotators. Contrasting previous studies of zero-resource hallucination detection, our method and benchmark concentrate on passage-level detection instead of sentence-level. We empirically evaluate our method and existing zero-resource detection methods on two datasets. The experimental results demonstrate that the proposed method considerably outperforms the baselines while costing fewer tokens and less time. Furthermore, we manually analyze some hallucination cases that LLM failed to capture, revealing the shared limitation of zero-resource methods.

Multi-level Contrastive Learning for Script-based Character Understanding

In this work, we tackle the scenario of understanding characters in scripts, which aims to learn the characters' personalities and identities from their utterances. We begin by analyzing several challenges in this scenario, and then propose a multi-level contrastive learning framework to capture characters' global information in a fine-grained manner. To validate the proposed framework, we conduct extensive experiments on three character understanding sub-tasks by comparing with strong pre-trained language models, including SpanBERT, Longformer, BigBird and ChatGPT-3.5. Experimental results demonstrate that our method improves the performances by a considerable margin. Through further in-depth analysis, we show the effectiveness of our method in addressing the challenges and provide more hints on the scenario of character understanding. We will open-source our work on github at https://github.com/David-Li0406/Script-based-Character-Understanding.

A New Dataset and Empirical Study for Sentence Simplification in Chinese

Sentence Simplification is a valuable technique that can benefit language learners and children a lot. However, current research focuses more on English sentence simplification. The development of Chinese sentence simplification is relatively slow due to the lack of data. To alleviate this limitation, this paper introduces CSS, a new dataset for assessing sentence simplification in Chinese. We collect manual simplifications from human annotators and perform data analysis to show the difference between English and Chinese sentence simplifications. Furthermore, we test several unsupervised and zero/few-shot learning methods on CSS and analyze the automatic evaluation and human evaluation results. In the end, we explore whether Large Language Models can serve as high-quality Chinese sentence simplification systems by evaluating them on CSS.

Human-like Summarization Evaluation with ChatGPT

Evaluating text summarization is a challenging problem, and existing evaluation metrics are far from satisfactory. In this study, we explored ChatGPT's ability to perform human-like summarization evaluation using four human evaluation methods on five datasets. We found that ChatGPT was able to complete annotations relatively smoothly using Likert scale scoring, pairwise comparison, Pyramid, and binary factuality evaluation. Additionally, it outperformed commonly used automatic evaluation metrics on some datasets. Furthermore, we discussed the impact of different prompts, compared its performance with that of human evaluation, and analyzed the generated explanations and invalid responses.

LAD-RCNN:A Powerful Tool for Livestock Face Detection and Normalization

With the demand for standardized large-scale livestock farming and the development of artificial intelligence technology, a lot of research in area of animal face recognition were carried on pigs, cattle, sheep and other livestock. Face recognition consists of three sub-task: face detection, face normalizing and face identification. Most of animal face recognition study focuses on face detection and face identification. Animals are often uncooperative when taking photos, so the collected animal face images are often in arbitrary directions. The use of non-standard images may significantly reduce the performance of face recognition system. However, there is no study on normalizing of the animal face image with arbitrary directions. In this study, we developed a light-weight angle detection and region-based convolutional network (LAD-RCNN) containing a new rotation angle coding method that can detect the rotation angle and the location of animal face in one-stage. LAD-RCNN has a frame rate of 72.74 FPS (including all steps) on a single GeForce RTX 2080 Ti GPU. LAD-RCNN has been evaluated on multiple dataset including goat dataset and gaot infrared image. Evaluation result show that the AP of face detection was more than 95% and the deviation between the detected rotation angle and the ground-truth rotation angle were less than 0.036 (i.e. 6.48{\deg}) on all the test dataset. This shows that LAD-RCNN has excellent performance on livestock face and its direction detection, and therefore it is very suitable for livestock face detection and Normalizing. Code is available at https://github.com/SheepBreedingLab-HZAU/LAD-RCNN/

Fine-grained Contrastive Learning for Definition Generation

Recently, pre-trained transformer-based models have achieved great success in the task of definition generation (DG). However, previous encoder-decoder models lack effective representation learning to contain full semantic components of the given word, which leads to generating under-specific definitions. To address this problem, we propose a novel contrastive learning method, encouraging the model to capture more detailed semantic representations from the definition sequence encoding. According to both automatic and manual evaluation, the experimental results on three mainstream benchmarks demonstrate that the proposed method could generate more specific and high-quality definitions compared with several state-of-the-art models.