Related papers: PUG: A Framework and Practical Implementation for …

Despite recent success in natural language processing (NLP), fact verification still remains a difficult task. Due to misinformation spreading increasingly fast, attention has been directed towards automatically verifying the correctness of…

Automatic question generation is an important technique that can improve the training of question answering, help chatbots to start or continue a conversation with humans, and provide assessment materials for educational purposes. Existing…

Most research in reading comprehension has focused on answering questions based on individual documents or even single paragraphs. We introduce a neural model which integrates and reasons relying on information spread within documents and…

Extending CoT through RL has been widely used to enhance the reasoning capabilities of LLMs. However, due to the sparsity of reward signals, it can also induce undesirable thinking patterns such as overthinking, i.e., generating redundant…

Personalized review generation (PRG) aims to automatically produce review text reflecting user preference, which is a challenging natural language generation task. Most of previous studies do not explicitly model factual description of…

In evolutionary computation, it is commonly assumed that a search algorithm acquires knowledge about a problem instance by sampling solutions from the search space and evaluating them with a fitness function. This is necessarily inefficient…

Applying deductive verification to formally prove that a program respects its formal specification is a very complex and time-consuming task due in particular to the lack of feedback in case of proof failures. Along with a non-compliance…

Logical table-to-text generation is a task that involves generating logically faithful sentences from tables, which requires models to derive logical level facts from table records via logical inference. It raises a new challenge on the…

In recent years, graph prompting has emerged as a promising research direction, enabling the learning of additional tokens or subgraphs appended to the original graphs without requiring retraining of pre-trained graph models across various…

The application of Large Language Models to Question Answering has shown great promise, but important challenges such as hallucinations and erroneous reasoning arise when using these models, particularly in knowledge-intensive,…

We target the problem of provably computing the equivalence between two complex expression trees. To this end, we formalize the problem of equivalence between two such programs as finding a set of semantics-preserving rewrite rules from one…

Test-time scaling has emerged as an effective way to improve language models on challenging reasoning tasks. However, most existing methods treat each problem in isolation and do not systematically reuse knowledge from prior reasoning…

Retrieval Augmented Generation (RAG) works as a backbone for interacting with an enterprise's own data via Conversational Question Answering (ConvQA). In a RAG system, a retriever fetches passages from a collection in response to a…

Current methods for embedding-based query answering over incomplete Knowledge Graphs (KGs) only focus on inductive reasoning, i.e., predicting answers by learning patterns from the data, and lack the complementary ability to do deductive…

Machine learning models that operate on graph-structured data, such as molecular graphs or social networks, often make accurate predictions but offer little insight into why certain predictions are made. Counterfactual explanations address…

Finding Minimal Unsatisfiable Subsets (MUSes) of binary constraints is a common problem in infeasibility analysis of over-constrained systems. However, because of the exponential search space of the problem, enumerating MUSes is extremely…

In Textual question answering (TQA) systems, complex questions often require retrieving multiple textual fact chains with multiple reasoning steps. While existing benchmarks are limited to single-chain or single-hop retrieval scenarios. In…

Natural question generation (QG) aims to generate questions from a passage and an answer. In this paper, we propose a novel reinforcement learning (RL) based graph-to-sequence (Graph2Seq) model for QG. Our model consists of a Graph2Seq…

Determining trust of data available in the Semantic Web is fundamental for applications and users, in particular for linked open data obtained from SPARQL endpoints. There exist several proposals in the literature to annotate SPARQL query…

Promptly and accurately answering questions on products is important for e-commerce applications. Manually answering product questions (e.g. on community question answering platforms) results in slow response and does not scale. Recent…