相关论文: Harnessing Consistency for Robust Test-Time LLM En…

Recent advancements in reasoning-reinforced Large Language Models (LLMs) have shown remarkable capabilities in complex reasoning tasks. However, the mechanism underlying their utilization of different human reasoning skills remains poorly…

Large language models (LLMs) have achieved impressive performance in code generation recently, offering programmers revolutionary assistance in software development. However, due to the auto-regressive nature of LLMs, they are susceptible…

Employing large language models (LLMs) to enable embodied agents has become popular, yet it presents several limitations in practice. In this work, rather than using LLMs directly as agents, we explore their use as tools for embodied agent…

The remarkable success of Large Language Models (LLMs) has ushered natural language processing (NLP) research into a new era. Despite their diverse capabilities, LLMs trained on different corpora exhibit varying strengths and weaknesses,…

Large Language Models (LLMs) have shown remarkable capabilities across various natural language processing tasks but often struggle to excel uniformly in diverse or complex domains. We propose a novel ensemble method - Diverse Fingerprint…

Ensembling large language models (LLMs) can effectively combine diverse strengths of different models, offering a promising approach to enhance performance across various tasks. However, existing methods typically rely on fixed weighting…

Although Large Language Models (LLMs) perform well in general fields, they exhibit a confidence distortion problem on multi-choice question-answering (MCQA), particularly as the number of answer choices increases. Specifically, on MCQA with…

While Large Language Models (LLMs) have demonstrated impressive capabilities, their output quality remains inconsistent across various application scenarios, making it difficult to identify trustworthy responses, especially in complex tasks…

Assessing the stability of code generation from large language models (LLMs) is essential for judging their reliability in real-world development. We extend prior "structural-entropy concepts" to the program domain by pairing entropy with…

As Large Language Models (LLMs) are increasingly adopted in edge intelligence to power domain-specific applications and personalized services, the quality and efficiency of the LLM post-training phase-including fine-tuning and inference,…

Large Language Models (LLMs) have achieved remarkable success in tasks requiring complex reasoning, such as code generation, mathematical problem solving, and algorithmic synthesis -- especially when aided by reasoning tokens and…

A Large Language Model (LLM) is considered consistent if semantically equivalent prompts produce semantically equivalent responses. Despite recent advancements showcasing the impressive capabilities of LLMs in conversational systems, we…

Large language models (LLMs) with mixture-of-experts (MoE) architectures achieve remarkable scalability by sparsely activating a subset of experts per token, yet their frequent expert switching creates memory bandwidth bottlenecks that…

Large language models (LLMs) can generate programs that pass unit tests, but passing tests does not guarantee reliable runtime behavior. We find that different correct solutions to the same task can show very different memory and…

Hallucinations are a persistent problem with Large Language Models (LLMs). As these models become increasingly used in high-stakes domains, such as healthcare and finance, the need for effective hallucination detection is crucial. To this…

In recent years, Multimodal Large Language Models (MLLMs) have achieved remarkable progress on a wide range of multimodal benchmarks. Despite these advances, most existing benchmarks mainly focus on single-image or multi-image…

Despite the superior performance of Large Reasoning Models (LRMs), their reasoning behaviors are often counterintuitive, leading to suboptimal reasoning capabilities. To theoretically formalize the desired reasoning behaviors, this paper…

Despite LLMs' excellent code creation capabilities, multilingual code generation remains extremely challenging. To address this, we intent to improve the multi-programming-lingual (MultiPL) performance of the base LLMs while retaining the…

This paper aims to overcome the "lost-in-the-middle" challenge of large language models (LLMs). While recent advancements have successfully enabled LLMs to perform stable language modeling with up to 4 million tokens, the persistent…

Large language models (LLMs) achieve strong average performance yet remain unreliable at the instance level, with frequent hallucinations, brittle failures, and poorly calibrated confidence. We study reliability through the lens of…