Related papers: De Jure: Iterative LLM Self-Refinement for Structu…

Large language models (LLMs) are increasingly used in scientific domains. While they can produce reasoning-like content via methods such as chain-of-thought prompting, these outputs are typically unstructured and informal, obscuring whether…

With the advent of artificial intelligence (AI), many researchers are attempting to extract structured information from document-level biomedical literature by fine-tuning large language models (LLMs). However, they face significant…

Despite advances in machine learning (ML) and large language models (LLMs), rule-based natural language processing (NLP) systems remain active in clinical settings due to their interpretability and operational efficiency. However, their…

LLM applications are AI systems whose nondeterministic outputs and evolving model behavior make traditional testing insufficient for release governance. We present an automated self-testing framework that introduces quality gates with…

In recent years, Large Language Models (LLMs) have been widely applied to legal tasks. To enhance their understanding of legal texts and improve reasoning accuracy, a promising approach is to incorporate legal theories. One of the most…

Large Language Models (LLMs) have demonstrated impressive performance across diverse domains, yet they still encounter challenges such as insufficient domain-specific knowledge, biases, and hallucinations. This underscores the need for…

Autoformalization plays a crucial role in formal mathematical reasoning by enabling the automatic translation of natural language statements into formal languages. While recent advances using large language models (LLMs) have shown…

Legal documents are unstructured, use legal jargon, and have considerable length, making them difficult to process automatically via conventional text processing techniques. A legal document processing system would benefit substantially if…

Instruction following is a key capability for LLMs. However, recent studies have shown that LLMs often struggle with instructions containing multiple constraints (e.g. a request to create a social media post "in a funny tone" with "no…

Structured information extraction from unstructured text is critical for emerging Software 3.0 systems where LLM agents autonomously interact with APIs and tools. Recent approaches apply large language models directly to extraction tasks…

Automatically extracting workflows as procedural graphs from natural language is promising yet underexplored, demanding both structural validity and logical alignment. While recent large language models (LLMs) show potential for procedural…

Document-level Relation Triplet Extraction (DocRTE) is a fundamental task in information systems that aims to simultaneously extract entities with semantic relations from a document. Existing methods heavily rely on a substantial amount of…

Systematic reviews and meta-analyses rely on converting narrative articles into structured, numerically grounded study records. Despite rapid advances in large language models (LLMs), it remains unclear whether they can meet the structural…

Relevance judgments are crucial for evaluating information retrieval systems, but traditional human-annotated labels are time-consuming and expensive. As a result, many researchers turn to automatic alternatives to accelerate method…

Speculative decoding accelerates LLM inference by verifying candidate tokens from a draft model against a larger target model. Recent judge decoding boosts this process by relaxing verification criteria by accepting draft tokens that may…

Automation in software engineering increasingly relies on large language models (LLMs) to generate, review, and assess code artifacts. However, establishing LLMs as reliable evaluators remains an open challenge: human evaluations are…

As Large Language Models (LLMs) become integrated into high-stakes domains, there is a growing need for evaluation methods that are both scalable for real-time deployment and reliable for critical decision-making. While human evaluation is…

The exponential growth of financial research has rendered traditional systematic literature reviews (SLRs) increasingly impractical, as manual screening and narrative synthesis struggle to keep pace with the scale and complexity of modern…

Large Reasoning Models (LRMs) have demonstrated strong performance by producing extended Chain-of-Thought (CoT) traces before answering. However, this paradigm often induces over-reasoning: redundant calculations and circular…

Automated judgment document generation is a significant yet challenging legal AI task. As the conclusive written instrument issued by a court, a judgment document embodies complex legal reasoning. However, existing methods often…