Large language models (LLMs) demonstrate great performance in text generation. However, LLMs are still suffering from hallucinations. In this work, we propose an inference-time method, Self-Highlighted Hesitation (SH2), to help LLMs decode more truthfully. SH2 is based on a simple fact rooted in information theory that for an LLM, the tokens predicted with lower probabilities are prone to be more informative than others. Our analysis shows that these low-confidence tokens are more likely to be closely related to factual information, such as nouns, proper nouns, and adjectives. Therefore, we propose to ”highlight” the factual information by selecting key tokens with the lowest probabilities and concatenating them to the original context, thus forcing the model to repeatedly read and hesitate on these tokens before generation. During decoding, we also adopt contrastive decoding to emphasize the difference in output probabilities brought by the hesitation. Experimental results demonstrate that our SH2, requiring no additional data or models, can effectively help LLMs elicit factual knowledge and distinguish hallucinated contexts by themselves. Significant and consistent improvements are achieved by SH2 for LLaMA-7b, LLaMA2-7b and Mistral-7b on various hallucination tasks.

In this work, we present the largest benchmark to date on linguistic acceptability: Multilingual Evaluation of Linguistic Acceptability—MELA, with 46K samples covering 10 languages from a diverse set of language families. We establish LLM baselines on this benchmark, and investigate cross-lingual transfer in acceptability judgements with XLM-R. In pursuit of multilingual interpretability, we conduct probing experiments with fine-tuned XLM-R to explore the process of syntax capability acquisition. Our results show that GPT-4o exhibits a strong multilingual ability, outperforming fine-tuned XLM-R, while open-source multilingual models lag behind by a noticeable gap. Cross-lingual transfer experiments show that transfer in acceptability judgment is non-trivial: 500 Icelandic fine-tuning examples lead to 23 MCC performance in a completely unrelated language—Chinese. Results of our probing experiments indicate that training on MELA improves the performance of XLM-R on syntax-related tasks.

Against the backdrop of the ever-improving Natural Language Inference (NLI) models, recent efforts have focused on the suitability of the current NLI datasets and on the feasibility of the NLI task as it is currently approached. Many of the recent studies have exposed the inherent human disagreements of the inference task and have proposed a shift from categorical labels to human subjective probability assessments, capturing human uncertainty. In this work, we show how neither the current task formulation nor the proposed uncertainty gradient are entirely suitable for solving the NLI challenges. Instead, we propose an ordered sense space annotation, which distinguishes between logical and common-sense inference. One end of the space captures non-sensical inferences, while the other end represents strictly logical scenarios. In the middle of the space, we find a continuum of common-sense, namely, the subjective and graded opinion of a “person on the street.” To arrive at the proposed annotation scheme, we perform a careful investigation of the SICK corpus and we create a taxonomy of annotation issues and guidelines. We re-annotate the corpus with the proposed annotation scheme, utilizing four symbolic inference systems, and then perform a thorough evaluation of the scheme by fine-tuning and testing commonly used pre-trained language models on the re-annotated SICK within various settings. We also pioneer a crowd annotation of a small portion of the MultiNLI corpus, showcasing that it is possible to adapt our scheme for annotation by non-experts on another NLI corpus. Our work shows the efficiency and benefits of the proposed mechanism and opens the way for a careful NLI task refinement.

The advent of natural language understanding (NLU) benchmarks for English, such as GLUE and SuperGLUE allows new NLU models to be evaluated across a diverse set of tasks. These comprehensive benchmarks have facilitated a broad range of research and applications in natural language processing (NLP). The problem, however, is that most such benchmarks are limited to English, which has made it difficult to replicate many of the successes in English NLU for other languages. To help remedy this issue, we introduce the first large-scale Chinese Language Understanding Evaluation (CLUE) benchmark. CLUE is an open-ended, community-driven project that brings together 9 tasks spanning several well-established single-sentence/sentence-pair classification tasks, as well as machine reading comprehension, all on original Chinese text. To establish results on these tasks, we report scores using an exhaustive set of current state-of-the-art pre-trained Chinese models (9 in total). We also introduce a number of supplementary datasets and additional tools to help facilitate further progress on Chinese NLU. Our benchmark is released at https://www.cluebenchmarks.com

Despite the tremendous recent progress on natural language inference (NLI), driven largely by large-scale investment in new datasets (e.g.,SNLI, MNLI) and advances in modeling, most progress has been limited to English due to a lack of reliable datasets for most of the world’s languages. In this paper, we present the first large-scale NLI dataset (consisting of ~56,000 annotated sentence pairs) for Chinese called the Original Chinese Natural Language Inference dataset (OCNLI). Unlike recent attempts at extending NLI to other languages, our dataset does not rely on any automatic translation or non-expert annotation. Instead, we elicit annotations from native speakers specializing in linguistics. We follow closely the annotation protocol used for MNLI, but create new strategies for eliciting diverse hypotheses. We establish several baseline results on our dataset using state-of-the-art pre-trained models for Chinese, and find even the best performing models to be far outpaced by human performance (~12% absolute performance gap), making it a challenging new resource that we hope will help to accelerate progress in Chinese NLU. To the best of our knowledge, this is the first human-elicited MNLI-style corpus for a non-English language.

This paper describes a working system which performs natural language inference using polarity-marked parse trees. The system handles all of the instances of monotonicity inference in the FraCaS data set. Except for the initial parse, it is entirely deterministic. It handles multi-premise arguments, and the kind of inference performed is essentially “logical”, but it goes beyond what is representable in first-order logic. In any case, the system works on surface forms rather than on representations of any kind.

This paper describes the IUCL system at VarDial 2019 evaluation campaign for the task of discriminating between Mainland and Taiwan variation of mandarin Chinese. We first build several base classifiers, including a Naive Bayes classifier with word n-gram as features, SVMs with both character and syntactic features, and neural networks with pre-trained character/word embeddings. Then we adopt ensemble methods to combine output from base classifiers to make final predictions. Our ensemble models achieve the highest F1 score (0.893) in simplified Chinese track and the second highest (0.901) in traditional Chinese track. Our results demonstrate the effectiveness and robustness of the ensemble methods.

We present a machine learning approach to distinguish texts translated to Chinese (by humans) from texts originally written in Chinese, with a focus on a wide range of syntactic features. Using Support Vector Machines (SVMs) as classifier on a genre-balanced corpus in translation studies of Chinese, we find that constituent parse trees and dependency triples as features without lexical information perform very well on the task, with an F-measure above 90%, close to the results of lexical n-gram features, without the risk of learning topic information rather than translation features. Thus, we claim syntactic features alone can accurately distinguish translated from original Chinese. Translated Chinese exhibits an increased use of determiners, subject position pronouns, NP + “的” as NP modifiers, multiple NPs or VPs conjoined by "、", among other structures. We also interpret the syntactic features with reference to previous translation studies in Chinese, particularly the usage of pronouns.

This paper shows how to take parse trees in CCG and algorithmically find the polarities of all the constituents. Our work uses the well-known polarization principle corresponding to function application, and we have extended this with principles for type raising and composition. We provide an algorithm, extending the polarity marking algorithm of van Benthem. We discuss how our system works in practice, taking input from the C&C parser.

Parsing Chinese critically depends on correct word segmentation for the parser since incorrect segmentation inevitably causes incorrect parses. We investigate a pipeline approach to segmentation and parsing using word lattices as parser input. We compare CRF-based and lexicon-based approaches to word segmentation. Our results show that the lattice parser is capable of selecting the correction segmentation from thousands of options, thus drastically reducing the number of unparsed sentence. Lexicon-based parsing models have a better coverage than the CRF-based approach, but the many options are more difficult to handle. We reach our best result by using a lexicon from the n-best CRF analyses, combined with highly probable words.