Related papers: Towards Relational Contextual Equality Saturation

Large Language Models cannot reliably acquire new knowledge post-deployment -- even when relevant text resources exist, models fail to transform them into actionable knowledge without retraining. Retrieval-Augmented Generation attempts to…

Generalisation in machine learning often relies on the ability to encode structures present in data into an inductive bias of the model class. To understand the power of quantum machine learning, it is therefore crucial to identify the…

Modern sequential recommender systems commonly use transformer-based models for next-item prediction. While these models demonstrate a strong balance between efficiency and quality, integrating interleaving features - such as the query…

Retrieval Augmented Generation (RAG) is a framework for incorporating external knowledge, usually in the form of a set of documents retrieved from a collection, as a part of a prompt to a large language model (LLM) to potentially improve…

In this article, we discuss a flow--sensitive analysis of equality relationships for imperative programs. We describe its semantic domains, general purpose operations over abstract computational states (term evaluation and identification,…

It is well-known that document context is vital for resolving a range of translation ambiguities, and in fact the document setting is the most natural setting for nearly all translation. It is therefore unfortunate that machine translation…

Evaluating retrieval-augmented generation (RAG) presents challenges, particularly for retrieval models within these systems. Traditional end-to-end evaluation methods are computationally expensive. Furthermore, evaluation of the retrieval…

Large language models (LLMs) have revolutionized natural language processing (NLP), particularly through Retrieval-Augmented Generation (RAG), which enhances LLM capabilities by integrating external knowledge. However, traditional RAG…

Extended sequence generation often leads to degradation in contextual consistency due to the inability of conventional self-attention mechanisms to effectively retain long-range dependencies. Existing approaches, including memory…

Interactive theorem provers, like Isabelle/HOL, Coq and Lean, have expressive languages that allow the formalization of general mathematical objects and proofs. In this context, an important goal is to reduce the time and effort needed to…

Benchmarking plays an important role in the development of novel search algorithms as well as for the assessment and comparison of contemporary algorithmic ideas. This paper presents common principles that need to be taken into account when…

This work combines information about the dialogue history encoded by pre-trained model with a meaning representation of the current system utterance to realize contextual language generation in task-oriented dialogues. We utilize the…

Current conversational passage retrieval systems cast conversational search into ad-hoc search by using an intermediate query resolution step that places the user's question in context of the conversation. While the proposed methods have…

Recently, Large Language Models (LLMs) have demonstrated remarkable advancements in Natural Language Processing (NLP). However, generating high-quality text that balances coherence, diversity, and relevance remains challenging. Traditional…

Recent Long-Context Language Models (LCLMs) can process hundreds of thousands of tokens in a single prompt, enabling new opportunities for knowledge-intensive multi-hop reasoning by integrating large sets of retrieved documents or, in some…

Semantic matching is of central importance to many natural language tasks \cite{bordes2014semantic,RetrievalQA}. A successful matching algorithm needs to adequately model the internal structures of language objects and the interaction…

Representation learning plays a central role in structuring internal embeddings to capture the statistical properties of language, influencing the coherence and contextual consistency of generated text. Statistical Coherence Alignment is…

Lexical substitution is the task of generating meaningful substitutes for a word in a given textual context. Contextual word embedding models have achieved state-of-the-art results in the lexical substitution task by relying on contextual…

Software security can be ensured by specifying and verifying security properties of software using formal methods with strong theoretical bases. In particular, programs can be modeled in the framework of lambda-calculi, and interesting…

Word alignment, which aims to align translationally equivalent words between source and target sentences, plays an important role in many natural language processing tasks. Current unsupervised neural alignment methods focus on inducing…