paper-with-me

홈 › Papers

What are Models Thinking about? Understanding Large Language Model Hallucinations "Psychology" through Model Inner State Analysis

2025-02-19 · Peiran Wang, Yang Liu, Yunfei Lu, Jue Hong, Ye Wu

Large language model (LLM) systems suffer from the models' unstable ability to generate valid and factual content, resulting in hallucination generation. Current hallucination detection methods heavily rely on out-of-model information sources, such as RAG to assist the detection, thus bringing heavy additional latency. Recently, internal states of LLMs' inference have been widely used in numerous research works, such as prompt injection detection, etc. Considering the interpretability of LLM internal states and the fact that they do not require external information sources, we introduce such states into LLM hallucination detection. In this paper, we systematically analyze different internal states' revealing features during inference forward and comprehensively evaluate their ability in hallucination detection. Specifically, we cut the forward process of a large language model into three stages: understanding, query, generation, and extracting the internal state from these stages. By analyzing these states, we provide a deep understanding of why the hallucinated content is generated and what happened in the internal state of the models. Then, we introduce these internal states into hallucination detection and conduct comprehensive experiments to discuss the advantages and limitations.

📄 PDF Abstract BibTeX arXiv:2502.13490

Code (0)

등록된 구현이 없습니다.

Tasks

HallucinationLanguage ModelingLanguage ModellingLarge Language ModelmodelRAGvalid

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Adam 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Weight Decay 설명 없음
BART BART is a denoising autoencoder for pretraining sequence-to-sequence models. It is trained by (1) corrupting text…

Similar Papers 제목 키워드 기반

Some hypotheses on how chatbots work in problem-solving-driven conversations. Large Language Models as confirmation of the Innovation Illusion

2026-06-05 · S. F. M. van Vlijmen, H. D. Lethe arxiv

We discuss the nature of chatbots as conversation partners in problem-solving. What can chatbots do and what can't they do? We develop hypotheses on how this can this be explained. Our argument draws on insights from Agg…

LLMs and the ZPD

2026-05-12 · Peter Wallis arxiv

One hundred years ago Vygotsky and his circle were exploring the nature of consciousness and defining what would become psychology in the Soviet Union. They concluded that children develop "scientific thinking" through i…

Do Thought Streams Matter? Evaluating Reasoning in Gemini Vision-Language Models for Video Scene Understanding

2026-04-13 · Shivam Sharma, Sankalp Nagaonkar, Ashish Choithani, Ashutosh Trivedi arxiv

We benchmark how internal reasoning traces, which we call thought streams, affect video scene understanding in vision-language models. Using four configurations of Google's Gemini 2.5 Flash and Flash Lite across scenes e…

Scene Understanding

Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?

2022-02-25 · Sewon Min, Xinxi Lyu, Ari Holtzman, Mikel Artetxe 외

Large language models (LMs) are able to in-context learn -- perform a new task via inference alone by conditioning on a few input-label pairs (demonstrations) and making predictions for new inputs. However, there has bee…

In-Context Learning

What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective

2024-10-31 · Ming Li, Yanhong Li, Tianyi Zhou

What makes a difference in the post-training of LLMs? We investigate the training patterns of different layers in large language models (LLMs), through the lens of gradient, when training with different responses and ini…