LLM & NLP

This paper introduces RuleArena, a novel and challenging benchmark designed to evaluate the ability of large language models (LLMs) to follow complex, real-world rules in reasoning. Covering three practical domains – airline baggage fees, NBA transactions, and tax regulations – RuleArena assesses LLMs’ proficiency in handling intricate natural language instructions that demand long-context understanding, logical reasoning, and accurate mathematical computation. Two key attributes distinguish RuleArena from traditional rule-based reasoning benchmarks – (1) it extends beyond standard first-order logic representations, and (2) it is grounded in authentic, practical scenarios, providing insights into the suitability and reliability of LLMs for real-world applications. Our findings reveal several notable limitations in LLMs – (1) they struggle to identify and apply the appropriate rules, frequently becoming confused by similar but distinct regulations, (2) they cannot consistently perform accurate mathematical computations, even when they correctly identify the relevant rules, and (3) in general, they perform poorly in the benchmark. These results highlight significant challenges in advancing LLMs’ rule-guided reasoning capabilities in real-life applications.

This study intends to systematically disentangle pure logic reasoning and text understanding by investigating the contrast across abstract and contextualized logical problems from a comprehensive set of domains. We explore whether LLMs demonstrate genuine reasoning capabilities across various domains when the underlying logical structure remains constant. We focus on two main questions (1) Can abstract logical problems alone accurately benchmark an LLM’s reasoning ability in real-world scenarios, disentangled from contextual support in practical settings? (2) Does fine-tuning LLMs on abstract logic problem generalize to contextualized logic problems and vice versa? To investigate these questions, we focus on standard propositional logic, specifically propositional deductive and abductive logic reasoning. In particular, we construct instantiated datasets for deductive and abductive reasoning with 4 levels of difficulty, encompassing 12 distinct categories or domains based on the categorization of Wikipedia. Our experiments aim to provide insights into disentangling context in logical reasoning and the true reasoning capabilities of LLMs and their generalization potential.

Current approaches of knowledge editing struggle to effectively propagate updates to interconnected facts. In this work, we delve into the barriers that hinder the appropriate propagation of updated knowledge within these models for accurate reasoning. To support our analysis, we introduce a novel reasoning-based benchmark – ReCoE (Reasoning-based Counterfactual Editing dataset) – which covers six common reasoning schemes in real world. We conduct a thorough analysis of existing knowledge editing techniques, including input augmentation, finetuning, and locate-and-edit. We found that all model editing methods show notably low performance on this dataset, especially in certain reasoning schemes. Our analysis over the chain-of-thought generation of edited models further uncover key reasons behind the inadequacy of existing knowledge editing methods from a reasoning standpoint, involving aspects on fact-wise editing, fact recall ability, and coherence in generation. We will make our benchmark publicly available.

Current natural language processing (NLP) models such as BERT and RoBERTa have achieved high overall performance, but they often make systematic errors due to bias or certain difficult features to learn. Thus research on slice detection models (SDM) which automatically identifies underperforming groups of datapoints has gradually caught more attention, which aims at both understanding model behaviors and providing insights for future model training and designing. However, there is little systematic research on SDM and quantitative evaluation of its assessment for NLP models. Our paper fills this gap by proposing “Discover, Explanation, Improvement” framework that discovers coherent and underperforming groups of datapoints and unites datapoints of each slice under human-understandable concepts; it also provides comprehensive evaluation tasks and the corresponding quantitative metrics, which enable convenient comparison for future works. Results show that our framework can accurately select error-prone datapoints with informative semantic features that summarize error patterns, based on which it directly boosts model performance by an average of 2.85 points based on trained models without tuning any parameters across multiple datasets.

Logical reasoning is a challenge for many current NLP neural network models since it requires more than the ability of learning informative representations from data. Inspired by the Dual Process Theory in cognitive science—which proposes that human cognition process involves two stages – an intuitive, unconscious and fast process relying on perception calledSystem 1, and a logical, conscious and slow process performing complex reasoning called System 2—we leverage neural logic reasoning (System 2) on top of the representation learning models (System 1), which conducts explicit neural-based differentiable logical reasoning on top of the representations learned by the base neural models. Based on experiments on the commonsense knowledge graph completion task, we show that the two-system architecture always improves from its System 1 model alone. Experiments also show that both the rule-driven logical regularizer and the data-driven value regularizer are important and the performance improvement is marginal without the two regularizers, which indicates that learning from both logical prior and training data is important for reasoning tasks.

A conventional approach to entity linking is to first find mentions in a given document and then infer their underlying entities in the knowledge base. A well-known limitation of this approach is that it requires finding mentions without knowing their entities, which is unnatural and difficult. We present a new model that does not suffer from this limitation called EntQA, which stands for Entity linking as Question Answering. EntQA first proposes candidate entities with a fast retrieval module, and then scrutinizes the document to find mentions of each candidate with a powerful reader module. Our approach combines progress in entity linking with that in open-domain question answering and capitalizes on pretrained models for dense entity retrieval and reading comprehension. Unlike in previous works, we do not rely on a mention-candidates dictionary or large-scale weak supervision. EntQA achieves strong results on the GERBIL benchmarking platform.

Existing OIE (Open Information Extraction) algorithms are independent of each other such that there exist lots of redundant works; the featured strategies are not reusable and not adaptive to new tasks. This paper proposes a new pipeline to build OIE systems, where an Open-domain Information eXpression (OIX) task is proposed to provide a platform for all OIE strategies. The OIX is an OIE friendly expression of a sentence without information loss. The generation procedure of OIX contains shared works of OIE algorithms so that OIE strategies can be developed on the platform of OIX as inference operations focusing on more critical problems. Based on the same platform of OIX, the OIE strategies are reusable, and people can select a set of strategies to assemble their algorithm for a specific task so that the adaptability may be significantly increased. This paper focuses on the task of OIX and propose a solution–Open Information Annotation (OIA). OIA is a predicate-function-argument annotation for sentences. We label a data set of sentence-OIA pairs and propose a dependency-based rule system to generate OIA annotations from sentences. The evaluation results reveal that learning the OIA from a sentence is a challenge owing to the complexity of natural language sentences, and it is worthy of attracting more attention from the research community.