English
Related papers

Related papers: The Hydra Effect: Emergent Self-repair in Language…

200 papers

Large language models often reason beyond surface tokens, but the internal stage at which token-level information becomes abstract relational structure remains unclear. We investigate this question by analyzing how attention heads and…

Artificial Intelligence · Computer Science 2026-05-22 Junjie Zhang , Zhen Shen , Xisong Dong , Gang Xiong

Intrinsic self-correction in Large Language Models (LLMs) frequently fails in open-ended reasoning tasks due to ``hallucination snowballing,'' a phenomenon in which models recursively justify early errors during free-text reflection. While…

Computation and Language · Computer Science 2026-04-08 Hongxu Zhou

Symbolic perturbations offer a novel approach for influencing neural representations without requiring direct modification of model parameters. The recursive regeneration of symbolic structures introduces structured variations in latent…

Computation and Language · Computer Science 2025-08-11 Kathlyn Eaglewood , Tobias Featherington , Dorian Mayfair , Sylvester Grimshaw , James Pettigrew

OpenAI has recently argued that hallucinations in large language models result primarily from misaligned evaluation incentives that reward confident guessing rather than epistemic humility. On this view, hallucination is a contingent…

Computation and Language · Computer Science 2025-12-18 Richard Ackermann , Simeon Emanuilov

Large Language Models (LLMs) have demonstrated an unprecedented ability to simulate human-like social behaviors, making them useful tools for simulating complex social systems. However, it remains unclear to what extent these simulations…

Social and Information Networks · Computer Science 2026-04-16 Erica Cau , Andrea Failla , Giulio Rossetti

Variational autoencoders have been widely applied for natural language generation, however, there are two long-standing problems: information under-representation and posterior collapse. The former arises from the fact that only the last…

Machine Learning · Computer Science 2021-06-17 Xianghong Fang , Haoli Bai , Zenglin Xu , Michael Lyu , Irwin King

Large Language Models (LLMs) have shown propensity to generate hallucinated outputs, i.e., texts that are factually incorrect or unsupported. Existing methods for alleviating hallucinations typically require costly human annotations to…

Computation and Language · Computer Science 2024-04-03 Yu Xia , Xu Liu , Tong Yu , Sungchul Kim , Ryan A. Rossi , Anup Rao , Tung Mai , Shuai Li

Language models draw on two knowledge sources: facts baked into weights (parametric memory, PM) and information in context (working memory, WM). We study two mechanistically distinct failure modes--conflict, when PM and WM disagree and…

Artificial Intelligence · Computer Science 2026-05-15 Qiyao Liang , Risto Miikkulainen , Ila Fiete

We explore which linguistic factors -- at the sentence and token level -- play an important role in influencing language model predictions, and investigate whether these are reflective of results found in humans and human corpora (Gries and…

Computation and Language · Computer Science 2024-09-18 Jaap Jumelet , Willem Zuidema , Arabella Sinclair

Large Language Models (LLMs) are known to exhibit social, demographic, and gender biases, often as a consequence of the data on which they are trained. In this work, we adopt a mechanistic interpretability approach to analyze how such…

Computation and Language · Computer Science 2025-06-09 Bhavik Chandna , Zubair Bashir , Procheta Sen

Large Language Models (LLMs) are known to overuse certain terms like "delve" and "intricate." The exact reasons for these lexical choices, however, have been unclear. Using Meta's Llama model, this study investigates the contribution of…

Computation and Language · Computer Science 2025-08-05 Tom S. Juzek , Zina B. Ward

This paper presents a systematic defense of large language model (LLM) hallucinations or 'confabulations' as a potential resource instead of a categorically negative pitfall. The standard view is that confabulations are inherently…

Computation and Language · Computer Science 2024-06-27 Peiqi Sui , Eamon Duede , Sophie Wu , Richard Jean So

Multimodal Large Language Models often suffer from object hallucination. While existing research utilizes attention enhancement and visual retracing, we find these works lack sufficient interpretability regarding attention drift in final…

Computer Vision and Pattern Recognition · Computer Science 2026-03-27 Chengxu Yang , Jingling Yuan , Chuang Hu , Jiawei Jiang

Language models have shown strong capabilities across a wide range of tasks in software engineering, such as code generation, yet they suffer from hallucinations. While hallucinations have been studied independently in natural language and…

Software Engineering · Computer Science 2025-08-13 Chunhua Liu , Hong Yi Lin , Patanamon Thongtanunam

The stability of recursively trained large language models (LLMs) is a foundational problem for AI safety. Prevailing theory predicts model collapse, a progressive degradation when models are trained on their own output. We challenge this…

Machine Learning · Computer Science 2025-09-16 Sai Teja Reddy Adapala

Hallucinations, a phenomenon where a language model (LM) generates nonfactual content, pose a significant challenge to the practical deployment of LMs. While many empirical methods have been proposed to mitigate hallucinations, recent…

Computation and Language · Computer Science 2026-05-18 Atsushi Suzuki , Yulan He , Feng Tian , Zhongyuan Wang

Large language models (LLMs) excel on a variety of reasoning benchmarks, but previous studies suggest they sometimes struggle to generalize to unseen questions, potentially due to over-reliance on memorized training examples. However, the…

Computation and Language · Computer Science 2025-04-01 Yihuai Hong , Dian Zhou , Meng Cao , Lei Yu , Zhijing Jin

The emergence of Large Language Models (LLMs) has revolutionized how users access information, shifting from traditional search engines to direct question-and-answer interactions with LLMs. However, the widespread adoption of LLMs has…

Computation and Language · Computer Science 2024-07-23 Weihang Su , Yichen Tang , Qingyao Ai , Changyue Wang , Zhijing Wu , Yiqun Liu

Large language models (LLMs) are increasingly being adopted as the cognitive core of embodied agents. However, inherited hallucinations, which stem from failures to ground user instructions in the observed physical environment, can lead to…

Large language models (LLMs) are increasingly used as alternatives to traditional search engines given their capacity to generate text that resembles human language. However, this shift is concerning, as LLMs often generate hallucinations,…

Computation and Language · Computer Science 2024-10-25 Cléa Chataigner , Afaf Taïk , Golnoosh Farnadi