The Hallucinations Leaderboard -- An Open Effort to Measure Hallucinations in Large Language Models

Large Language Models (LLMs) have transformed the Natural Language Processing (NLP) landscape with their remarkable ability to understand and generate human-like text. However, these models are prone to ``hallucinations'' -- outputs that do not align with factual reality or the input context. This paper introduces the Hallucinations Leaderboard, an open initiative to quantitatively measure and compare the tendency of each model to produce hallucinations. The leaderboard uses a comprehensive set of benchmarks focusing on different aspects of hallucinations, such as factuality and faithfulness, across various tasks, including question-answering, summarisation, and reading comprehension. Our analysis provides insights into the performance of different models, guiding researchers and practitioners in choosing the most reliable models for their applications.

Beyond prompting: Making Pre-trained Language Models Better Zero-shot Learners by Clustering Representations

Recent work has demonstrated that pre-trained language models (PLMs) are zero-shot learners. However, most existing zero-shot methods involve heavy human engineering or complicated self-training pipelines, hindering their application to new situations. In this work, we show that zero-shot text classification can be improved simply by clustering texts in the embedding spaces of PLMs. Specifically, we fit the unlabeled texts with a Bayesian Gaussian Mixture Model after initializing cluster positions and shapes using class names. Despite its simplicity, this approach achieves superior or comparable performance on both topic and sentiment classification datasets and outperforms prior works significantly on unbalanced datasets. We further explore the applicability of our clustering approach by evaluating it on 14 datasets with more diverse topics, text lengths, and numbers of classes. Our approach achieves an average of 20% absolute improvement over prompt-based zero-shot learning. Finally, we compare different PLM embedding spaces and find that texts are well-clustered by topics even if the PLM is not explicitly pre-trained to generate meaningful sentence embeddings. This work indicates that PLM embeddings can categorize texts without task-specific fine-tuning, thus providing a new way to analyze and utilize their knowledge and zero-shot learning ability.

Anticipating the Unseen Discrepancy for Vision and Language Navigation

Vision-Language Navigation requires the agent to follow natural language instructions to reach a specific target. The large discrepancy between seen and unseen environments makes it challenging for the agent to generalize well. Previous studies propose data augmentation methods to mitigate the data bias explicitly or implicitly and provide improvements in generalization. However, they try to memorize augmented trajectories and ignore the distribution shifts under unseen environments at test time. In this paper, we propose an Unseen Discrepancy Anticipating Vision and Language Navigation (DAVIS) that learns to generalize to unseen environments via encouraging test-time visual consistency. Specifically, we devise: 1) a semi-supervised framework DAVIS that leverages visual consistency signals across similar semantic observations. 2) a two-stage learning procedure that encourages adaptation to test-time distribution. The framework enhances the basic mixture of imitation and reinforcement learning with Momentum Contrast to encourage stable decision-making on similar observations under a joint training stage and a test-time adaptation stage. Extensive experiments show that DAVIS achieves model-agnostic improvement over previous state-of-the-art VLN baselines on R2R and RxR benchmarks. Our source code and data are in supplemental materials.

MIC: Model-agnostic Integrated Cross-channel Recommenders

Semantically connecting users and items is a fundamental problem for the matching stage of an industrial recommender system. Recent advances in this topic are based on multi-channel retrieval to efficiently measure users' interest on items from the massive candidate pool. However, existing work are primarily built upon pre-defined retrieval channels, including User-CF (U2U), Item-CF (I2I), and Embedding-based Retrieval (U2I), thus access to the limited correlation between users and items which solely entail from partial information of latent interactions. In this paper, we propose a model-agnostic integrated cross-channel (MIC) approach for the large-scale recommendation, which maximally leverages the inherent multi-channel mutual information to enhance the matching performance. Specifically, MIC robustly models correlation within user-item, user-user, and item-item from latent interactions in a universal schema. For each channel, MIC naturally aligns pairs with semantic similarity and distinguishes them otherwise with more uniform anisotropic representation space. While state-of-the-art methods require specific architectural design, MIC intuitively considers them as a whole by enabling the complete information flow among users and items. Thus MIC can be easily plugged into other retrieval recommender systems. Extensive experiments show that our MIC helps several state-of-the-art models boost their performance on two real-world benchmarks. The satisfactory deployment of the proposed MIC on industrial online services empirically proves its scalability and flexibility.

DDRQA: Dynamic Document Reranking for Open-domain Multi-hop Question Answering

Open-domain multi-hop question answering (QA) requires to retrieve multiple supporting documents, some of which have little lexical overlap with the question and can only be located by iterative document retrieval. However, multi-step document retrieval often incurs more relevant but non-supporting documents, which dampens the downstream noise-sensitive reader module for answer extraction. To address this challenge, we propose Dynamic Document Reranking (DDR) to iteratively retrieve, rerank and filter documents, and adaptively determine when to stop the retrieval process. DDR employs an entity-linked document graph for multi-document interaction, which boosts up the retrieval performance. Experiments on HotpotQA full wiki setting show that our method achieves more than 7 points higher reranking performance over the previous best retrieval model, and also achieves state-of-the-art question answering performance on the official leaderboard.

A Pairwise Probe for Understanding BERT Fine-Tuning on Machine Reading Comprehension

Pre-trained models have brought significant improvements to many NLP tasks and have been extensively analyzed. But little is known about the effect of fine-tuning on specific tasks. Intuitively, people may agree that a pre-trained model already learns semantic representations of words (e.g. synonyms are closer to each other) and fine-tuning further improves its capabilities which require more complicated reasoning (e.g. coreference resolution, entity boundary detection, etc). However, how to verify these arguments analytically and quantitatively is a challenging task and there are few works focus on this topic. In this paper, inspired by the observation that most probing tasks involve identifying matched pairs of phrases (e.g. coreference requires matching an entity and a pronoun), we propose a pairwise probe to understand BERT fine-tuning on the machine reading comprehension (MRC) task. Specifically, we identify five phenomena in MRC. According to pairwise probing tasks, we compare the performance of each layer's hidden representation of pre-trained and fine-tuned BERT. The proposed pairwise probe alleviates the problem of distraction from inaccurate model training and makes a robust and quantitative comparison. Our experimental analysis leads to highly confident conclusions: (1) Fine-tuning has little effect on the fundamental and low-level information and general semantic tasks. (2) For specific abilities required for downstream tasks, fine-tuned BERT is better than pre-trained BERT and such gaps are obvious after the fifth layer.

DC-BERT: Decoupling Question and Document for Efficient Contextual Encoding

Recent studies on open-domain question answering have achieved prominent performance improvement using pre-trained language models such as BERT. State-of-the-art approaches typically follow the "retrieve and read" pipeline and employ BERT-based reranker to filter retrieved documents before feeding them into the reader module. The BERT retriever takes as input the concatenation of question and each retrieved document. Despite the success of these approaches in terms of QA accuracy, due to the concatenation, they can barely handle high-throughput of incoming questions each with a large collection of retrieved documents. To address the efficiency problem, we propose DC-BERT, a decoupled contextual encoding framework that has dual BERT models: an online BERT which encodes the question only once, and an offline BERT which pre-encodes all the documents and caches their encodings. On SQuAD Open and Natural Questions Open datasets, DC-BERT achieves 10x speedup on document retrieval, while retaining most (about 98%) of the QA performance compared to state-of-the-art approaches for open-domain question answering.

Glyce: Glyph-vectors for Chinese Character Representations

It is intuitive that NLP tasks for logographic languages like Chinese should benefit from the use of the glyph information in those languages. However, due to the lack of rich pictographic evidence in glyphs and the weak generalization ability of standard computer vision models on character data, an effective way to utilize the glyph information remains to be found. In this paper, we address this gap by presenting the Glyce, the glyph-vectors for Chinese character representations. We make three major innovations: (1) We use historical Chinese scripts (e.g., bronzeware script, seal script, traditional Chinese, etc) to enrich the pictographic evidence in characters; (2) We design CNN structures tailored to Chinese character image processing; and (3) We use image-classification as an auxiliary task in a multi-task learning setup to increase the model's ability to generalize. For the first time, we show that glyph-based models are able to consistently outperform word/char ID-based models in a wide range of Chinese NLP tasks. Using Glyce, we are able to achieve the state-of-the-art performances on 13 (almost all) Chinese NLP tasks, including (1) character-Level language modeling, (2) word-Level language modeling, (3) Chinese word segmentation, (4) name entity recognition, (5) part-of-speech tagging, (6) dependency parsing, (7) semantic role labeling, (8) sentence semantic similarity, (9) sentence intention identification, (10) Chinese-English machine translation, (11) sentiment analysis, (12) document classification and (13) discourse parsing