Unlike English, which uses distinct forms (e.g., had, has, will have) to mark the perfect aspect across tenses, Chinese and Japanese lack separate grammatical forms for tense within the perfect aspect, which complicates Natural Language Inference (NLI). Focusing on the perfect aspect in these languages, we construct a linguistically motivated, template-based NLI dataset (1,350 pairs per language). Experiments reveal that even advanced LLMs struggle with temporal inference, particularly in detecting subtle tense and reference-time shifts. These findings highlight model limitations and underscore the need for cross-linguistic evaluation in temporal semantics. Our dataset is available at https://github.com/Lujie2001/CrossNLI.

While fine-tuning LLMs on NLI corpora improves their inferential performance, the underlying mechanisms driving this improvement remain largely opaque. In this work, we conduct a series of experiments to investigate what LLMs actually learn during fine-tuning. We begin by analyzing predicate frequencies in premises and hypotheses across NLI datasets and identify a consistent frequency bias, where predicates in hypotheses occur more frequently than those in premises for positive instances. To assess the impact of this bias, we evaluate both standard and NLI fine-tuned LLMs on bias-consistent and bias-adversarial cases. We find that LLMs exploit frequency bias for inference and perform poorly on adversarial instances. Furthermore, fine-tuned LLMs exhibit significantly increased reliance on this bias, suggesting that they are learning these frequency patterns from datasets. Finally, we compute the frequencies of hyponyms and their corresponding hypernyms from WordNet, revealing a correlation between frequency bias and textual entailment. These findings help explain why learning frequency patterns can enhance model performance on inference tasks.

We introduce FinNLI, a benchmark dataset for Financial Natural Language Inference (FinNLI) across diverse financial texts like SEC Filings, Annual Reports, and Earnings Call transcripts. Our dataset framework ensures diverse premise-hypothesis pairs while minimizing spurious correlations. FinNLI comprises 21,304 pairs, including a high-quality test set of 3,304 instances annotated by finance experts. Evaluations show that domain shift significantly degrades general-domain NLI performance. The highest Macro F1 scores for pre-trained (PLMs) and large language models (LLMs) baselines are 74.57% and 78.62%, respectively, highlighting the dataset's difficulty. Surprisingly, instruction-tuned financial LLMs perform poorly, suggesting limited generalizability. FinNLI exposes weaknesses in current LLMs for financial reasoning, indicating room for improvement.

LLMs are often claimed to be capable of Natural Language Inference (NLI), which is widely regarded as a cornerstone of more complex forms of reasoning. However, recent works show that LLMs still suffer from hallucinations in NLI due to attestation bias, where LLMs overly rely on propositional memory to build shortcuts. To solve the issue, we design an unsupervised framework to construct counterfactual reasoning data and fine-tune LLMs to reduce attestation bias. To measure bias reduction, we build bias-adversarial variants of NLI datasets with randomly replaced predicates in premises while keeping hypotheses unchanged. Extensive evaluations show that our framework can significantly reduce hallucinations from attestation bias. Then, we further evaluate LLMs fine-tuned with our framework on original NLI datasets and their bias-neutralized versions, where original entities are replaced with randomly sampled ones. Extensive results show that our framework consistently improves inferential performance on both original and bias-neutralized NLI datasets.

We revisit the reference determinacy (RD) assumption in the task of natural language inference (NLI), i.e., the premise and hypothesis are assumed to refer to the same context when human raters annotate a label. While RD is a practical assumption for constructing a new NLI dataset, we observe that current NLI models, which are typically trained solely on hypothesis-premise pairs created with the RD assumption, fail in downstream applications such as fact verification, where the input premise and hypothesis may refer to different contexts. To highlight the impact of this phenomenon in real-world use cases, we introduce RefNLI, a diagnostic benchmark for identifying reference ambiguity in NLI examples. In RefNLI, the premise is retrieved from a knowledge source (i.e., Wikipedia) and does not necessarily refer to the same context as the hypothesis. With RefNLI, we demonstrate that finetuned NLI models and few-shot prompted LLMs both fail to recognize context mismatch, leading to over 80% false contradiction and over 50% entailment predictions. We discover that the existence of reference ambiguity in NLI examples can in part explain the inherent human disagreements in NLI and provide insight into how the RD assumption impacts the NLI dataset creation process.

Large Language Models, despite their significant capabilities, are known to fail in surprising and unpredictable ways. Evaluating their true `understanding' of language is particularly challenging due to the extensive web-scale data they are trained on. Therefore, we construct an evaluation to systematically assess natural language understanding (NLU) in LLMs by leveraging Construction Grammar (CxG), which provides insights into the meaning captured by linguistic elements known as constructions (Cxns). CxG is well-suited for this purpose because provides a theoretical basis to construct targeted evaluation sets. These datasets are carefully constructed to include examples which are unlikely to appear in pre-training data, yet intuitive and easy for humans to understand, enabling a more targeted and reliable assessment. Our experiments focus on downstream natural language inference and reasoning tasks by comparing LLMs' understanding of the underlying meanings communicated through 8 unique Cxns with that of humans. The results show that while LLMs demonstrate some knowledge of constructional information, even the latest models including GPT-o1 struggle with abstract meanings conveyed by these Cxns, as demonstrated in cases where test sentences are dissimilar to their pre-training data. We argue that such cases provide a more accurate test of true language understanding, highlighting key limitations in LLMs' semantic capabilities. We make our novel dataset and associated experimental data including prompts and model responses publicly available.

The task of scientific Natural Language Inference (NLI) involves predicting the semantic relation between two sentences extracted from research articles. This task was recently proposed along with a new dataset called SciNLI derived from papers published in the computational linguistics domain. In this paper, we aim to introduce diversity in the scientific NLI task and present MSciNLI, a dataset containing 132,320 sentence pairs extracted from five new scientific domains. The availability of multiple domains makes it possible to study domain shift for scientific NLI. We establish strong baselines on MSciNLI by fine-tuning Pre-trained Language Models (PLMs) and prompting Large Language Models (LLMs). The highest Macro F1 scores of PLM and LLM baselines are 77.21% and 51.77%, respectively, illustrating that MSciNLI is challenging for both types of models. Furthermore, we show that domain shift degrades the performance of scientific NLI models which demonstrates the diverse characteristics of different domains in our dataset. Finally, we use both scientific NLI datasets in an intermediate task transfer learning setting and show that they can improve the performance of downstream tasks in the scientific domain. We make our dataset and code available on Github.

In NLP, zero-shot classification (ZSC) is the task of assigning labels to textual data without any labeled examples for the target classes. A common method for ZSC is to fine-tune a language model on a Natural Language Inference (NLI) dataset and then use it to infer the entailment between the input document and the target labels. However, this approach faces certain challenges, particularly for languages with limited resources. In this paper, we propose an alternative solution that leverages dictionaries as a source of data for ZSC. We focus on Luxembourgish, a low-resource language spoken in Luxembourg, and construct two new topic relevance classification datasets based on a dictionary that provides various synonyms, word translations and example sentences. We evaluate the usability of our dataset and compare it with the NLI-based approach on two topic classification tasks in a zero-shot manner. Our results show that by using the dictionary-based dataset, the trained models outperform the ones following the NLI-based approach for ZSC. While we focus on a single low-resource language in this study, we believe that the efficacy of our approach can also transfer to other languages where such a dictionary is available.