Related papers: RP-Rewriter: An Optimized Rewriter for Large Terms…

Man-made 3D shapes are naturally organized in parts and hierarchies; such structures provide important constraints for shape reconstruction and generation. Modeling shape structures is difficult, because there can be multiple hierarchies…

Patent analysis and mining are time-consuming and costly processes for companies, but nevertheless essential if they are willing to remain competitive. To face the overload induced by numerous patents, the idea is to automatically filter…

We describe defret-mutual-generate, a utility for proving ACL2 theorems about large mutually recursive cliques of functions. This builds on previous tools such as defret-mutual and make-flag, which automate parts of the process but still…

This work suggests fundamentally rethinking the current practice of pruning large language models (LLMs). The way it is done is by divide and conquer: split the model into submodels, sequentially prune them, and reconstruct predictions of…

Large language models(LLMs) containing tens of billions of parameters (or even more) have demonstrated impressive capabilities in various NLP tasks. However, substantial model size poses challenges to training, inference, and deployment so…

Summarizing lengthy documents is a common and essential task in our daily lives. Although recent advancements in neural summarization models can assist in crafting general-purpose summaries, human writers often have specific requirements…

Retrieval-augmented large language models (LLMs) leverage relevant content retrieved by information retrieval systems to generate correct responses, aiming to alleviate the hallucination problem. However, existing retriever-responder…

We present a neural program synthesis approach integrating components which write, execute, and assess code to navigate the search space of possible programs. We equip the search process with an interpreter or a read-eval-print-loop (REPL),…

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…

String rewriting systems have proved very useful to study monoids. In good cases, they give finite presentations of monoids, allowing computations on those and their manipulation by a computer. Even better, when the presentation is…

Motivated by an application where we try to make proofs for Description Logic inferences smaller by rewriting, we consider the following decision problem, which we call the small term reachability problem: given a term rewriting system $R$,…

We report on an inversion tool for a class of oriented conditional constructor term rewriting systems. Four well-behaved rule inverters ranging from trivial to full, partial and semi-inverters are included. Conditional term rewriting…

Large Reasoning Models (LRMs) demonstrate strong performance on complex tasks but often suffer from excessive verbosity, known as "overthinking." Existing solutions via reinforcement learning (RL) typically penalize generated tokens to…

We present REMARK-LLM, a novel efficient, and robust watermarking framework designed for texts generated by large language models (LLMs). Synthesizing human-like content using LLMs necessitates vast computational resources and extensive…

Reinforcement learning (RL) is a powerful tool for solving complex decision-making problems, but its lack of transparency and interpretability has been a major challenge in domains where decisions have significant real-world consequences.…

Reinforcement learning (RL) has demonstrated significant promise in enhancing the reasoning capabilities of Text2SQL LLMs, especially with advanced algorithms such as GRPO and DAPO. However, the performance of these methods is highly…

This paper is an extended abstract of an analysis of term rewriting where the terms in the rewrite rules as well as the term to be rewritten are compressed by a singleton tree grammar (STG). This form of compression is more general than…

In this paper, we propose R$^3$: Learning Reasoning through Reverse Curriculum Reinforcement Learning (RL), a novel method that employs only outcome supervision to achieve the benefits of process supervision for large language models. The…

Smart contracts are tools with self-execution capabilities that provide enhanced security compared to traditional contracts; however, their immutability makes post-deployment fault correction extremely complex, highlighting the need for a…

An important challenge in constraint programming is to rewrite constraint models into executable programs calculat- ing the solutions. This phase of constraint processing may require translations between constraint programming lan- guages,…