相关论文: Entropy and Attention Dynamics in Small Language M…

Reliable question answering with large language models (LLMs) is challenged by hallucinations, fluent but factually incorrect outputs arising from epistemic uncertainty. Existing entropy-based semantic-level uncertainty estimation methods…

Recent work has shown that the hidden states of large language models contain signals useful for uncertainty estimation and hallucination detection, motivating a growing interest in efficient probe-based approaches. Yet it remains unclear…

Reasoning VLMs can become more accurate while progressively losing visual grounding as they think. This creates task-conditional danger zones where low-entropy predictions are confident but ungrounded, a failure mode text-only monitoring…

Large language models (LLMs) have recently shown impressive performance on tasks involving reasoning, leading to a lively debate on whether these models possess reasoning capabilities similar to humans. However, despite these successes, the…

The recent performance leap of Large Language Models (LLMs) opens up new opportunities across numerous industrial applications and domains. However, erroneous generations, such as false predictions, misinformation, and hallucination made by…

Despite the outstanding performance of large language models (LLMs) across various NLP tasks, hallucinations in LLMs--where LLMs generate inaccurate responses--remains as a critical problem as it can be directly connected to a crisis of…

Linear Attention Large Language Models (LLMs) offer a compelling recurrent formulation that compresses context into a fixed-size state matrix, enabling constant-time inference. However, the internal dynamics of this compressed state remain…

Language models (LMs) have already demonstrated remarkable abilities in understanding and generating both natural and formal language. Despite these advances, their integration with real-world environments such as large-scale knowledge…

Vision-language models (VLMs) frequently generate hallucinated content plausible but incorrect claims about image content. We propose a training-free self-correction framework enabling VLMs to iteratively refine responses through…

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…

As language models (LMs) deliver increasing performance on a range of NLP tasks, probing classifiers have become an indispensable technique in the effort to better understand their inner workings. A typical setup involves (1) defining an…

Practitioners have consistently observed three puzzling phenomena in transformer-based large language models (LLMs): attention sinks, value-state drains, and residual-state peaks, collectively referred to as extreme-token phenomena. These…

Existing studies have introduced method-based reasoning and scope extension as approaches to enhance Large Language Model (LLM) performance beyond direct matrix mappings. Building on these foundations, this paper summarizes and integrates…

Large language models (LLMs) often exhibit deficient reasoning or generate hallucinations. To address these, studies prefixed with "Self-" such as Self-Consistency, Self-Improve, and Self-Refine have been initiated. They share a…

Large Language Models (LLMs) are widely deployed in real-world applications, yet little is known about their training dynamics at the token level. Evaluation typically relies on aggregated training loss, measured at the batch level, which…

While LLMs have seen substantial improvement in reasoning capabilities, they also sometimes overthink, generating unnecessary reasoning steps, particularly under uncertainty, given ill-posed or ambiguous queries. We introduce statistically…

Large language models (LLMs) have revolutionized the field of natural language processing with their impressive reasoning and question-answering capabilities. However, these models are sometimes prone to generating credible-sounding but…

Can large language models detect and report their own internal states? A number of studies have argued that the answer to this question is yes. We argue, based on lessons from human metacognition research, that this conclusion may be…

Large Language Models (LLMs) have become increasingly pervasive, finding applications across many industries and disciplines. Ensuring the trustworthiness of LLM outputs is paramount, where Uncertainty Estimation (UE) plays a key role. In…

Entropy minimization (EM) trains the model to concentrate even more probability mass on its most confident outputs. We show that this simple objective alone, without any labeled data, can substantially improve large language models' (LLMs)…