English
Related papers

Related papers: Do Large Language Models Get Caught in Hofstadter-…

200 papers

Designing task-oriented dialogue systems is a challenging research topic, since it needs not only to generate utterances fulfilling user requests but also to guarantee the comprehensibility. Many previous works trained end-to-end (E2E)…

Computation and Language · Computer Science 2021-02-22 Jianhong Wang , Yuan Zhang , Tae-Kyun Kim , Yunjie Gu

Reasoning has become a central capability in large language models. Recent research has shown that reasoning performance can be improved by looping an LLM's layers in the latent dimension, resulting in looped reasoning language models.…

When the substantive content of a request is rewritten, do large language models still answer in the format the original task asked for? We find that they often do not, even at temperature zero. On a 150-query evaluation over five compact…

Computation and Language · Computer Science 2026-05-12 Aofan Liu , Jingxiang Meng

Hallucinations in multimodal large language models (MLLMs) -- where the model generates content inconsistent with the input image -- pose significant risks in real-world applications, from misinformation in visual question answering to…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Bingkui Tong , Jiaer Xia , Sifeng Shang , Kaiyang Zhou

Large language models are increasingly integrated into decision-making in areas such as healthcare, law, finance, engineering, and government. Yet they share a critical limitation: they produce fluent outputs even when their internal…

Artificial Intelligence · Computer Science 2026-04-17 Rikard Rosenbacke , Carl Rosenbacke , Victor Rosenbacke , Martin McKee

Safety alignment in large language models (LLMs) is primarily evaluated under open-ended generation, where models can mitigate risk by refusing to respond. In contrast, many real-world applications place LLMs in structured decision-making…

Computation and Language · Computer Science 2026-04-21 Yuheng Chen , Zhiyu Wu , Bowen Cheng , Tetsuro Takahashi

We identify a structural weakness in current large language model (LLM) alignment: modern refusal mechanisms are fail-open. While existing approaches encode refusal behaviors across multiple latent features, suppressing a single dominant…

Machine Learning · Computer Science 2026-02-20 Zachary Coalson , Beth Sohler , Aiden Gabriel , Sanghyun Hong

With the widespread adoption of large language models (LLMs), hallucinations, which are non-factual fabrications in model outputs, have become serious concerns. Reasoning capabilities have received attention as a self-verification process…

Computation and Language · Computer Science 2026-01-06 Junichiro Niimi

Large Language Models (LLMs) often exhibit sycophancy, distorting responses to align with user beliefs, notably by readily agreeing with user counterarguments. Paradoxically, LLMs are increasingly adopted as successful evaluative agents for…

Computation and Language · Computer Science 2025-09-23 Sungwon Kim , Daniel Khashabi

Large language models (LLMs) in research and development toolchains produce output that triggers attribution of agency and understanding -- a cognitive illusion that degrades verification behavior and trust calibration. No existing…

Software Engineering · Computer Science 2026-04-10 Marek Miller

LLM deployment in critical domains is currently impeded by persistent hallucinations--generating plausible but factually incorrect assertions. While scaling laws drove significant improvements in general capabilities, theoretical frameworks…

Machine Learning · Computer Science 2026-01-29 Jiayun Wu , Jiashuo Liu , Zhiyuan Zeng , Tianyang Zhan , Tianle Cai , Wenhao Huang

Hallucinations in large language models (LLMs) present a growing challenge across real-world applications, from healthcare to law, where factual reliability is essential. Despite advances in alignment and instruction tuning, LLMs can still…

Computation and Language · Computer Science 2025-05-02 Makoto Sato

Whether machines can originate novel content has been debated for nearly two centuries, from Lovelace's assertion that no engine can "originate anything" to Turing's question of whether a machine can amplify ideas brought in from outside.…

Multiagent Systems · Computer Science 2026-05-19 Weiyi Kong , Shiyang Lai , Jinghua Piao , James Evans

Large language models (large LMs) are susceptible to producing text that contains hallucinated content. An important instance of this problem is self-contradiction, where the LM generates two contradictory sentences within the same context.…

Computation and Language · Computer Science 2024-03-19 Niels Mündler , Jingxuan He , Slobodan Jenko , Martin Vechev

This project develops a self correcting framework for large language models (LLMs) that detects and mitigates hallucinations during multi-step reasoning. Rather than relying solely on final answer correctness, our approach leverages fine…

Artificial Intelligence · Computer Science 2025-11-21 Chelsea Zou , Yiheng Yao , Basant Khalil

Language models trained with reinforcement learning (RL) can engage in reward hacking--the exploitation of unintended strategies for high reward--without revealing this behavior in their chain-of-thought reasoning. This makes the detection…

Computation and Language · Computer Science 2025-07-15 Miles Turpin , Andy Arditi , Marvin Li , Joe Benton , Julian Michael

Large Language Models (LLMs) show remarkable capabilities, yet their stochastic next-token prediction creates logical inconsistencies and reward hacking that formal symbolic systems avoid. To bridge this gap, we introduce a formal logic…

Machine Learning · Computer Science 2026-02-02 Chuxue Cao , Jinluan Yang , Haoran Li , Kunhao Pan , Zijian Zhao , Zhengyu Chen , Yuchen Tian , Lijun Wu , Conghui He , Sirui Han , Yike Guo

Large reasoning models, such as OpenAI o1 and DeepSeek-R1, tend to become increasingly verbose as their reasoning capabilities improve. These inflated Chain-of-Thought (CoT) trajectories often exceed what the underlying problems require,…

Machine Learning · Computer Science 2026-05-12 Songtao Wei , Yi Li , Zhikai Li , Xu Hu , Yuede Ji , Guanpeng Li , Feng Chen , Carl Yang , Zhichun Guo , Bingzhe Li

Larger language models (LLMs) have taken the world by storm with their massive multi-tasking capabilities simply by optimizing over a next-word prediction objective. With the emergence of their properties and encoded knowledge, the risk of…

Computation and Language · Computer Science 2023-08-31 Rishabh Bhardwaj , Soujanya Poria

Current LLM safety research predominantly focuses on mitigating Goal Hijacking, preventing attackers from redirecting a model's high-level objective (e.g., from "summarizing emails" to "phishing users"). In this paper, we argue that this…

Cryptography and Security · Computer Science 2026-04-28 Yuansen Liu , Yixuan Tang , Anthony Kum Hoe Tun
‹ Prev 1 3 4 5 6 7 10 Next ›