Related papers: Towards Controllable Natural Language Inference th…

The rapid development of large language models (LLMs) gives rise to ethical concerns about their performance, while opening new avenues for developing toxic language detection techniques. However, LLMs' unethical output and their capability…

In this paper, we propose the TBCNN-pair model to recognize entailment and contradiction between two sentences. In our model, a tree-based convolutional neural network (TBCNN) captures sentence-level semantics; then heuristic matching…

We present a framework for deriving inference relations between Dutch sentence pairs. The proposed framework relies on logic-based reasoning to produce inspectable proofs leading up to inference labels; its judgements are therefore…

Large-scale pre-trained language models have demonstrated strong capabilities of generating realistic text. However, it remains challenging to control the generation results. Previous approaches such as prompting are far from sufficient,…

Financial institutions increasingly require AI explanations that are persistent, cross-validated across methods, and conversationally accessible to human decision-makers. We present an architecture for human-centered explainable AI in…

An emerging line of research in Explainable NLP is the creation of datasets enriched with human-annotated explanations and rationales, used to build and evaluate models with step-wise inference and explanation generation capabilities. While…

Generating natural language statements to convey logical inferences from tabular data (i.e., Logical NLG) is a process with one input and a variety of valid outputs. This characteristic underscores the need for a method to produce a diverse…

Text is by far the most ubiquitous source of knowledge and information and should be made easily accessible to as many people as possible; however, texts often contain complex words that hinder reading comprehension and accessibility.…

This paper investigates how hallucination rates in Large Language Models (LLMs) may be controlled via a symbolic data generation framework, exploring a fundamental relationship between the rate of certain mathematical errors and types of…

Controllers for structured LM reasoning (e.g., Chain-of-Thought, self-consistency, and Tree-of-Thoughts) often entangle what to try next with how to execute it, exposing only coarse global knobs and yielding brittle, compute-inefficient,…

Large language models (LLMs) often benefit from intermediate steps of reasoning to generate answers to complex problems. When these intermediate steps of reasoning are used to monitor the activity of the model, it is essential that this…

Developing explainability methods for Natural Language Processing (NLP) models is a challenging task, for two main reasons. First, the high dimensionality of the data (large number of tokens) results in low coverage and in turn small…

Abductive reasoning starts from some observations and aims at finding the most plausible explanation for these observations. To perform abduction, humans often make use of temporal and causal inferences, and knowledge about how some…

Reasoning in Large Language Models incurs significant inference-time compute, yet the token-level information structure of reasoning traces remains underexplored. We observe that reasoning tokens split into two functional types: low-entropy…

Natural language explanations play a fundamental role in Natural Language Inference (NLI) by revealing how premises logically entail hypotheses. Recent work has shown that the interaction of large language models (LLMs) with theorem provers…

Explaining the black-box predictions of NLP models naturally and accurately is an important open problem in natural language generation. These free-text explanations are expected to contain sufficient and carefully-selected evidence to form…

Natural language counterfactual generation aims to minimally modify a given text such that the modified text will be classified into a different class. The generated counterfactuals provide insight into the reasoning behind a model's…

Text generation aims to produce human-like natural language output for down-stream tasks. It covers a wide range of applications like machine translation, document summarization, dialogue generation and so on. Recently deep neural…

We present IBR, an Iterative Backward Reasoning model to solve the proof generation tasks on rule-based Question Answering (QA), where models are required to reason over a series of textual rules and facts to find out the related proof path…

Multi-step processes via large language models (LLMs) have proven effective for solving complex reasoning tasks. However, the depth of exploration of the reasoning procedure can significantly affect the task performance. Existing methods to…