Related papers: Learning Highly Recursive Input Grammars

We continue our study of ordered context-free grammars, a grammar formalism that places an order on the parse trees produced by the corresponding context-free grammar. In particular, we simplify our previous definition of a derivation of a…

Reading comprehension is a challenging task, especially when executed across longer or across multiple evidence documents, where the answer is likely to reoccur. Existing neural architectures typically do not scale to the entire evidence,…

A substantial thread of recent work on latent tree learning has attempted to develop neural network models with parse-valued latent variables and train them on non-parsing tasks, in the hope of having them discover interpretable tree…

Retrieval-Augmented Generation (RAG) grounds large language models with external evidence, but many implementations rely on pre-built indices that remain static after construction. Related queries therefore repeat similar multi-hop…

We introduce the Abductive Rule Learner with Context-awareness (ARLC), a model that solves abstract reasoning tasks based on Learn-VRF. ARLC features a novel and more broadly applicable training objective for abductive reasoning, resulting…

Attention-free language models that combine gating and convolutions are growing in popularity due to their efficiency and increasingly competitive performance. To better understand these architectures, we pretrain a suite of 17 attention…

Assumption-based Argumentation (ABA) is advocated as a unifying formalism for various forms of non-monotonic reasoning, including logic programming. It allows capturing defeasible knowledge, subject to argumentative debate. While, in much…

Search-based dialog models typically re-encode the dialog history at every turn, incurring high cost. Curved Contrastive Learning, a representation learning method that encodes relative distances between utterances into the embedding space…

The conversion from text to speech relies on the accurate mapping from linguistic to acoustic symbol sequences, for which current practice employs recurrent statistical models like recurrent neural networks. Despite the good performance of…

Large language models achieve strong performance on many complex reasoning tasks, yet their accuracy degrades sharply on benchmarks that require compositional reasoning, including ARC-AGI-2, GPQA, MATH, BBH, and HLE. Existing methods…

Retrieval-Augmented Generation RAG systems enhance large language models by grounding responses in external knowledge bases, but conventional RAG architectures operate with static corpora that cannot evolve from user interactions. We…

We propose a new, training-free method, Graph Reasoning via Retrieval Augmented Framework (GRRAF), that harnesses retrieval-augmented generation (RAG) alongside the code-generation capabilities of large language models (LLMs) to address a…

Robotic vision is a field where continual learning can play a significant role. An embodied agent operating in a complex environment subject to frequent and unpredictable changes is required to learn and adapt continuously. In the context…

High Recall Retrieval (HRR), such as eDiscovery and medical systematic review, is a search problem that optimizes the cost of retrieving most relevant documents in a given collection. Iterative approaches, such as iterative relevance…

Automatic generation of paraphrases from a given sentence is an important yet challenging task in natural language processing (NLP), and plays a key role in a number of applications such as question answering, search, and dialogue. In this…

In-context learning has recently been linked to implicit gradient descent in linear self-attention models, suggesting that context can induce a forward-pass update. Retrieval-augmented generation (RAG) also relies on context, but retrieved…

Syntactic rules in natural language typically need to make reference to hierarchical sentence structure. However, the simple examples that language learners receive are often equally compatible with linear rules. Children consistently…

Continual learning, also known as lifelong learning or incremental learning, refers to the process by which a model learns from a stream of incoming data over time. A common problem in continual learning is the classification layer's bias…

Speculative decoding aims to speed up autoregressive generation of a language model by verifying in parallel the tokens generated by a smaller draft model.In this work, we explore the effectiveness of learning-free, negligible-cost draft…

Conversational speech recognition is regarded as a challenging task due to its free-style speaking and long-term contextual dependencies. Prior work has explored the modeling of long-range context through RNNLM rescoring with improved…