Related papers: Extended Triangular Method: A Generalized Algorith…

Large language models (LLMs) have demonstrated remarkable capabilities in generating programs from natural language descriptions, yet ensuring their correctness without an external oracle remains a critical challenge. To solve the…

Test-Time Scaling (TTS) enhances the reasoning ability of large language models (LLMs) by allocating additional computation during inference. However, existing approaches primarily rely on output-level sampling while overlooking the role of…

Theorem proving serves as a major testbed for evaluating complex reasoning abilities in large language models (LLMs). However, traditional automated theorem proving (ATP) approaches rely heavily on formal proof systems that poorly align…

Large Language Models (LLMs) have shown impressive performance on complex tasks through Chain-of-Thought (CoT) reasoning. However, conventional CoT relies on explicitly verbalized intermediate steps, which constrains its broader…

Linear-time computational techniques have been developed for combining evidence which is available on a number of contending hypotheses. They offer a means of making the computation-intensive calculations involved more efficient in certain…

Chain-based reasoning methods like chain of thought (CoT) play a rising role in solving reasoning tasks for large language models (LLMs). However, the causal hallucinations between a step of reasoning and corresponding state transitions are…

Chain-of-thought (CoT) reasoning improves large language model performance on complex tasks, but often produces excessively long and inefficient reasoning traces. Existing methods shorten CoTs using length penalties or global entropy…

Recent works have demonstrated the effectiveness of retrieval augmentation in the Event Argument Extraction (EAE) task. However, existing retrieval-based EAE methods have two main limitations: (1) input length constraints and (2) the gap…

Current large language models (LLMs) primarily rely on linear sequence generation and massive parameter counts, yet they severely struggle with complex algorithmic reasoning. While recent reasoning architectures, such as the Hierarchical…

Although most of the automated theorem-proving approaches depend on formal proof systems, informal theorem proving can align better with large language models' (LLMs) strength in natural language processing. In this work, we identify a…

Machine learning algorithms in socially sensitive domains (e.g., credit decisions) often focus on equalizing predictive outcomes. However, satisfying these metrics does not guarantee that models use the same reasoning for different groups.…

Since the advent of Large Language Models a few years ago, they have often been considered the de facto solution for many AI problems. However, in addition to the many deficiencies of LLMs that prevent them from broad industry adoption,…

Automated theorem proving has long been a key task of artificial intelligence. Proofs form the bedrock of rigorous scientific inquiry. Many tools for both partially and fully automating their derivations have been developed over the last…

Ensuring the reliability of Large Language Models (LLMs) in complex reasoning tasks remains a formidable challenge, particularly in scenarios that demand precise mathematical calculations and knowledge-intensive open-domain generation. In…

The rapid spread of misinformation, driven by digital media and AI-generated content, has made automatic claim verification essential. Traditional methods, which depend on expert-annotated evidence, are labor-intensive and not scalable.…

The task of Text-to-SQL enables anyone to retrieve information from SQL databases using natural language. While this task has made substantial progress, the two primary evaluation metrics - Execution Accuracy (EXE) and Exact Set Matching…

In recent years, explainability in machine learning has gained importance. In this context, counterfactual explanation (CE), which is an explanation method that uses examples, has attracted attention. However, it has been pointed out that…

Emotion-Cause Pair Extraction (ECPE) involves extracting clause pairs representing emotions and their causes in a document. Existing methods tend to overfit spurious correlations, such as positional bias in existing benchmark datasets,…

Extended multi-adjoint logic programming arises as an extension of multi-adjoint normal logic programming where constraints and a special type of aggregator operator have been included. The use of this general aggregator operator permits to…

The LLM-as-a-judge paradigm uses large language models (LLMs) for automated text evaluation, where a numerical assessment is assigned by an LLM to the input text following scoring rubrics. Existing methods for LLM-as-a-judge use…