English
Related papers

Related papers: Super(ficial)-alignment: Strong Models May Deceive…

200 papers

Large language models (LLMs) are currently at the forefront of intertwining artificial intelligence (AI) systems with human communication and everyday life. Thus, aligning them with human values is of great importance. However, given the…

Computation and Language · Computer Science 2024-06-06 Thilo Hagendorff

The development of highly fluent large language models (LLMs) has prompted increased interest in assessing their reasoning and problem-solving capabilities. We investigate whether several LLMs can solve a classic type of deductive reasoning…

Computation and Language · Computer Science 2024-04-16 Spencer M. Seals , Valerie L. Shalin

With the introduction of (large) language models, there has been significant concern about the unintended bias such models may inherit from their training data. A number of studies have shown that such models propagate gender stereotypes,…

Computation and Language · Computer Science 2024-08-20 Rameez Qureshi , Naïm Es-Sebbani , Luis Galárraga , Yvette Graham , Miguel Couceiro , Zied Bouraoui

While fine-tuned language models perform well on many tasks, they were also shown to rely on superficial surface features such as lexical overlap. Excessive utilization of such heuristics can lead to failure on challenging inputs. We…

Computation and Language · Computer Science 2022-10-26 Elron Bandel , Yoav Goldberg , Yanai Elazar

Large language models have the potential to generate explanations for their own predictions in a variety of styles based on user instructions. Recent research has examined whether these self-explanations faithfully reflect the models'…

Computation and Language · Computer Science 2025-12-09 Tomoki Doi , Masaru Isonuma , Hitomi Yanaka

While large language models (LLMs) showcase unprecedented capabilities, they also exhibit certain inherent limitations when facing seemingly trivial tasks. A prime example is the recently debated "reversal curse", which surfaces when…

Computation and Language · Computer Science 2024-11-25 Zhengkai Lin , Zhihang Fu , Kai Liu , Liang Xie , Binbin Lin , Wenxiao Wang , Deng Cai , Yue Wu , Jieping Ye

As large language models attract increasing attention and find widespread application, concurrent challenges of reliability also arise at the same time. Confidence calibration, an effective analysis method for gauging the reliability of…

Computation and Language · Computer Science 2023-11-23 Chiwei Zhu , Benfeng Xu , Quan Wang , Yongdong Zhang , Zhendong Mao

While advances in fairness and alignment have helped mitigate overt biases exhibited by large language models (LLMs) when explicitly prompted, we hypothesize that these models may still exhibit implicit biases when simulating human…

Computation and Language · Computer Science 2025-01-30 Yuxuan Li , Hirokazu Shirado , Sauvik Das

Large language models (LLMs) are increasingly employed in information-seeking and decision-making tasks. Despite their broad utility, LLMs tend to generate information that conflicts with real-world facts, and their persuasive style can…

Computation and Language · Computer Science 2024-09-19 Arslan Chaudhry , Sridhar Thiagarajan , Dilan Gorur

Reward-model-based fine-tuning is a central paradigm in aligning Large Language Models with human preferences. However, such approaches critically rely on the assumption that proxy reward models accurately reflect intended supervision, a…

Computation and Language · Computer Science 2026-01-21 Zixuan Liu , Siavash H. Khajavi , Guangkai Jiang , Xinru Liu

Fine-tuning lets practitioners repurpose aligned large language models (LLMs) for new domains, yet recent work reveals emergent misalignment (EMA): Even a small, domain-specific fine-tune can induce harmful behaviors far outside the target…

Machine Learning · Computer Science 2026-03-06 David Kaczér , Magnus Jørgenvåg , Clemens Vetter , Esha Afzal , Robin Haselhorst , Lucie Flek , Florian Mai

As Large Language Models (LLMs) increasingly appear in social science research (e.g., economics and marketing), it becomes crucial to assess how well these models replicate human behavior. In this work, using hypothesis testing, we present…

Computers and Society · Computer Science 2025-06-19 Harbin Hong , Sebastian Caldas , Liu Leqi

Large language models (LLMs) are vulnerable to jailbreak attacks - resulting in harmful, unethical, or biased text generations. However, existing jailbreaking methods are computationally costly. In this paper, we propose the weak-to-strong…

Computation and Language · Computer Science 2025-07-25 Xuandong Zhao , Xianjun Yang , Tianyu Pang , Chao Du , Lei Li , Yu-Xiang Wang , William Yang Wang

As agentic AI becomes more widespread, agents with distinct and possibly conflicting goals will interact in complex ways. These multi-agent interactions pose a fundamental challenge, particularly in social dilemmas, where agents' individual…

Machine Learning · Computer Science 2025-12-02 Dereck Piche , Mohammed Muqeeth , Milad Aghajohari , Juan Duque , Michael Noukhovitch , Aaron Courville

Large language models (LLMs) have demonstrated remarkable capabilities across a wide range of natural language processing tasks. However, their tendency to exhibit sycophantic behavior - excessively agreeing with or flattering users - poses…

Computation and Language · Computer Science 2025-01-30 Lars Malmqvist

Successful deep learning models often involve training neural network architectures that contain more parameters than the number of training samples. Such overparametrized models have been extensively studied in recent years, and the…

Machine Learning · Computer Science 2024-02-02 Hamed Hassani , Adel Javanmard

Like students facing hard exam questions, large language models sometimes guess when uncertain, producing plausible yet incorrect statements instead of admitting uncertainty. Such "hallucinations" persist even in state-of-the-art systems…

Computation and Language · Computer Science 2025-09-08 Adam Tauman Kalai , Ofir Nachum , Santosh S. Vempala , Edwin Zhang

Story understanding and generation have long been a challenging task in natural language processing (NLP), especially when dealing with various levels of instruction specificity. In this paper, we propose a novel approach called "Weak to…

Computation and Language · Computer Science 2025-01-28 Yangshu Yuan , Heng Chen , Christian Ng

This work introduces a novel framework for evaluating LLMs' capacity to balance instruction-following with critical reasoning when presented with multiple-choice questions containing no valid answers. Through systematic evaluation across…

Computation and Language · Computer Science 2025-06-03 Gracjan Góral , Emilia Wiśnios , Piotr Sankowski , Paweł Budzianowski

Multimodal representation learning is fundamentally about transforming incomparable modalities into comparable representations. While prior research primarily focused on explicitly aligning these representations through targeted learning…

Machine Learning · Computer Science 2025-06-16 Megan Tjandrasuwita , Chanakya Ekbote , Liu Ziyin , Paul Pu Liang