Related papers: NCO: A Versatile Plug-in for Handling Negative Con…

Recent Large Reasoning Models (LRMs) have achieved remarkable performance in solving complex problems via supervised fine-tuning (SFT) and reinforcement learning (RL). Although existing RL algorithms significantly enhance model accuracy,…

Optimizing the trade-off among predictive performance and computational cost is a central focus in the deployment of Large Language Models (LLMs). Current routing methods primarily rely on direct mapping from queries to models based on…

The increasing prevalence of large language models (LLMs) such as GPT-4 in various applications has led to a surge in the size of prompts required for optimal performance, leading to challenges in computational efficiency. Prompt…

Although large language models (LLMs) have achieved significant success, their vulnerability to adversarial perturbations, including recent jailbreak attacks, has raised considerable concerns. However, the increasing size of these models…

Large language models (LLMs) have shown remarkable ability to generate code, yet their outputs often violate syntactic or semantic constraints when guided only through natural language prompts. We introduce TreeCoder, the most general and…

Despite strong performance on a variety of tasks, neural sequence models trained with maximum likelihood have been shown to exhibit issues such as length bias and degenerate repetition. We study the related issue of receiving…

Efficient inference in large language models (LLMs) has become a critical focus as their scale and complexity grow. Traditional autoregressive decoding, while effective, suffers from computational inefficiencies due to its sequential token…

As a medium for cold data storage, DNA stands out as it promises significant gains in storage capacity and lifetime. However, it comes with its own data processing challenges to overcome. Constrained codes over the DNA alphabet…

In-context learning has established itself as an important learning paradigm for Large Language Models (LLMs). In this paper, we demonstrate that LLMs can learn encoding keys in-context and perform analysis directly on encoded…

Detecting hate speech and offensive language is essential for maintaining a safe and respectful digital environment. This study examines the limitations of state-of-the-art large language models (LLMs) in identifying offensive content…

We present Pcodec (Pco), a format and algorithm for losslessly compressing numerical (float or integer) sequences. Pco's core and most novel component is a binning algorithm that quickly converges to the true entropy of smoothly,…

LLMs are increasingly applied to recommendation, retrieval, and reasoning, yet deploying a single end-to-end model that can jointly support these behaviors over large, heterogeneous catalogs remains challenging. Such systems must generate…

Intrinsic self-correct was a method that instructed large language models (LLMs) to verify and correct their responses without external feedback. Unfortunately, the study concluded that the LLMs could not self-correct reasoning yet. We find…

How can small-scale large language models (LLMs) efficiently utilize the supervision of LLMs to improve their generative quality? This question has been well studied in scenarios where there is no restriction on the number of LLM…

Automatic prompt optimization (APO) has driven significant gains in LLM-based agentic workflows. However, existing methods treat each task's prompt as a monolithic, instance-blind string optimized through global edits, producing brittle…

Large language models often suffer from language confusion, a phenomenon in which responses are partially or entirely generated in unintended languages. This critically degrades the user experience, especially in low-resource settings. We…

There is a growing interest in leveraging multiple large language models (LLMs) for automated code optimization. However, industrial platforms deploying multiple LLMs face a critical challenge: prompts optimized for one LLM often fail with…

Large Language Models (LLMs) have demonstrated a powerful ability for text generation. However, achieving optimal results with a given prompt or instruction can be challenging, especially for billion-sized models. Additionally, undesired…

The constructive approach within Neural Combinatorial Optimization (NCO) treats a combinatorial optimization problem as a finite Markov decision process, where solutions are built incrementally through a sequence of decisions guided by a…

Large language models (LLMs) have become proficient at sophisticated code-generation tasks, yet remain ineffective at reliably detecting or avoiding code vulnerabilities. Does this deficiency stem from insufficient learning about code…