English
Related papers

Related papers: Inside-Out: Hidden Factual Knowledge in LLMs

200 papers

Existing techniques for training language models can be misaligned with the truth: if we train models with imitation learning, they may reproduce errors that humans make; if we train them to generate text that humans rate highly, they may…

Computation and Language · Computer Science 2024-03-05 Collin Burns , Haotian Ye , Dan Klein , Jacob Steinhardt

Fact-seeking question answering with large language models (LLMs) remains unreliable when answers depend on up-to-date or conflicting information. Although retrieval-augmented and tool-using LLMs reduce hallucinations, they often rely on…

Computation and Language · Computer Science 2026-03-17 Auksarapak Kietkajornrit , Jad Tarifi , Nima Asgharbeygi

We study whether Large Language Models (LLMs) inherently capture domain-specific nuances in natural language. Our experiments probe the domain sensitivity of LLMs by examining their ability to distinguish queries from different domains…

Large Language Models (LLMs) have shown the impressive capability of answering questions in a wide range of scenarios. However, when LLMs face different types of questions, it is worth exploring whether LLMs are aware that some questions…

Computation and Language · Computer Science 2024-10-02 Dongjie Yang , Hai Zhao

Large language models (LLMs) have demonstrated impressive capabilities in various reasoning tasks, aided by techniques like chain-of-thought prompting that elicits verbalized reasoning. However, LLMs often generate text with obvious…

Artificial Intelligence · Computer Science 2024-12-06 Zhihui Xie , Jizhou Guo , Tong Yu , Shuai Li

Large Language Models (LLMs) are able to improve their responses when instructed to do so, a capability known as self-correction. When instructions provide only the task's goal without specific details about potential issues in the…

Computation and Language · Computer Science 2024-11-11 Guangliang Liu , Haitao Mao , Bochuan Cao , Zhiyu Xue , Xitong Zhang , Rongrong Wang , Jiliang Tang , Kristen Johnson

Large Language Models (LLMs) often struggle with producing factually consistent answers due to limitations in their parametric memory. Retrieval-Augmented Generation (RAG) paradigms mitigate this issue by incorporating external knowledge at…

Computation and Language · Computer Science 2026-05-05 Shanglin Wu , Lihui Liu , Jinho D. Choi , Kai Shu

By design, large language models (LLMs) are static general-purpose models, expensive to retrain or update frequently. As they are increasingly adopted for knowledge-intensive tasks, it becomes evident that these design choices lead to…

Computation and Language · Computer Science 2024-03-25 Shangbin Feng , Weijia Shi , Yuyang Bai , Vidhisha Balachandran , Tianxing He , Yulia Tsvetkov

Large language models (LLMs) outperform information retrieval techniques for downstream knowledge-intensive tasks when being prompted to generate world knowledge. However, community concerns abound regarding the factuality and potential…

Computation and Language · Computer Science 2023-10-12 Liang Chen , Yang Deng , Yatao Bian , Zeyu Qin , Bingzhe Wu , Tat-Seng Chua , Kam-Fai Wong

Standard factuality evaluations of LLMs treat all errors alike, obscuring whether failures arise from missing knowledge (empty shelves) or from limited access to encoded facts (lost keys). We propose a behavioral framework that profiles…

Computation and Language · Computer Science 2026-02-17 Nitay Calderon , Eyal Ben-David , Zorik Gekhman , Eran Ofek , Gal Yona

Large language models (LLMs) enable in-context learning (ICL) by conditioning on a few labeled training examples as a text-based prompt, eliminating the need for parameter updates and achieving competitive performance. In this paper, we…

Computation and Language · Computer Science 2024-04-02 Jianing Wang , Chengyu Wang , Chuanqi Tan , Jun Huang , Ming Gao

For Large Language Models (LLMs) to be reliable, they must learn robust knowledge that can be generally applied in diverse settings -- often unlike those seen during training. Yet, extensive research has shown that LLM performance can be…

Computation and Language · Computer Science 2025-10-15 Patrick Haller , Mark Ibrahim , Polina Kirichenko , Levent Sagun , Samuel J. Bell

Large Language Models (LLMs) have acquired ubiquitous attention for their performances across diverse domains. Our study here searches through LLMs' cognitive abilities and confidence dynamics. We dive deep into understanding the alignment…

Computation and Language · Computer Science 2023-09-29 Aniket Kumar Singh , Suman Devkota , Bishal Lamichhane , Uttam Dhakal , Chandra Dhakal

To reduce issues like hallucinations and lack of control in Large Language Models (LLMs), a common method is to generate responses by grounding on external contexts given as input, known as knowledge-augmented models. However, previous…

Computation and Language · Computer Science 2024-07-02 Hyunji Lee , Sejune Joo , Chaeeun Kim , Joel Jang , Doyoung Kim , Kyoung-Woon On , Minjoon Seo

While Large Language Models (LLMs) demonstrate impressive reasoning capabilities, growing evidence suggests much of their success stems from memorized answer-reasoning patterns rather than genuine inference. In this work, we investigate a…

Computation and Language · Computer Science 2025-06-24 Yang Wu , Yifan Zhang , Yiwei Wang , Yujun Cai , Yurong Wu , Yuran Wang , Ning Xu , Jian Cheng

Large Language Models (LLMs) can generate factually inaccurate content even if they have corresponding knowledge, which critically undermines their reliability. Existing approaches attempt to mitigate this by incorporating uncertainty in QA…

Computation and Language · Computer Science 2026-04-14 Xiaoning Dong , Chengyan Wu , Yajie Wen , Yu Chen , Yun Xue , Jing Zhang , Wei Xu , Bolei Ma

Despite their impressive capabilities, large language models (LLMs) frequently generate hallucinations. Previous work shows that their internal states encode rich signals of truthfulness, yet the origins and mechanisms of these signals…

Computation and Language · Computer Science 2026-04-16 Wen Luo , Guangyue Peng , Wei Li , Shaohang Wei , Feifan Song , Liang Wang , Nan Yang , Xingxing Zhang , Jing Jin , Furu Wei , Houfeng Wang

Large language models (LLMs) demonstrate the capacity to reconstruct and trace learned content from their training data under specific elicitation conditions, yet this capability does not manifest in standard generation contexts. This…

Computation and Language · Computer Science 2026-03-20 Toshiyuki Shigemura

Understanding what knowledge is implicitly encoded in deep learning models is essential for improving the interpretability of AI systems. This paper examines common methods to explain the knowledge encoded in word embeddings, which are core…

Computation and Language · Computer Science 2025-08-20 Hanna Herasimchyk , Alhassan Abdelhalim , Sören Laue , Michaela Regneri

As the applications of large language models (LLMs) expand across diverse fields, the ability of these models to adapt to ongoing changes in data, tasks, and user preferences becomes crucial. Traditional training methods, relying on static…

Machine Learning · Computer Science 2024-06-11 Junhao Zheng , Shengjie Qiu , Chengming Shi , Qianli Ma