English
Related papers

Related papers: The Alignment Bottleneck

200 papers

Alignment with human preferences is commonly framed using a universal reward function, even though human preferences are inherently heterogeneous. We formalize this heterogeneity by introducing user types and examine the limits of the…

Artificial Intelligence · Computer Science 2025-02-25 Ali Shirali , Arash Nasr-Esfahany , Abdullah Alomar , Parsa Mirtaheri , Rediet Abebe , Ariel Procaccia

We investigate how to exploit intermittent feedback for interference management. Focusing on the two-user linear deterministic interference channel, we completely characterize the capacity region. We find that the characterization only…

Information Theory · Computer Science 2016-11-17 Can Karakus , I-Hsiang Wang , Suhas Diggavi

Despite advances in large language models (LLMs) on reasoning and instruction-following tasks, it is unclear whether they can reliably produce outputs aligned with a variety of user goals, a concept called steerability. Two gaps in current…

Computation and Language · Computer Science 2026-01-21 Trenton Chang , Tobias Schnabel , Adith Swaminathan , Jenna Wiens

Despite significant advances in alignment techniques, we demonstrate that state-of-the-art language models remain vulnerable to carefully crafted conversational scenarios that can induce various forms of misalignment without explicit…

Computation and Language · Computer Science 2025-08-07 Siddhant Panpatil , Hiskias Dingeto , Haon Park

Large Language Models (LLMs) need to be aligned with human expectations to ensure their safety and utility in most applications. Alignment is challenging, costly, and needs to be repeated for every LLM and alignment criterion. We propose to…

Computation and Language · Computer Science 2024-10-07 Lilian Ngweta , Mayank Agarwal , Subha Maity , Alex Gittens , Yuekai Sun , Mikhail Yurochkin

Due to the remarkable capabilities and growing impact of large language models (LLMs), they have been deeply integrated into many aspects of society. Thus, ensuring their alignment with human values and intentions has emerged as a critical…

Large Language Models increasingly rely on self-explanations, such as chain of thought reasoning, to improve performance on multi step question answering. While these explanations enhance accuracy, they are often verbose and costly to…

Computation and Language · Computer Science 2026-02-17 Ali Zahedzadeh , Behnam Bahrak

Language model alignment has become an important component of AI safety, allowing safe interactions between humans and language models, by enhancing desired behaviors and inhibiting undesired ones. It is often done by tuning the model or…

Computation and Language · Computer Science 2025-05-28 Yotam Wolf , Noam Wies , Dorin Shteyman , Binyamin Rothberg , Yoav Levine , Amnon Shashua

Large Language Models produce sequences learned as statistical patterns from large corpora. In order not to reproduce corpus biases, after initial training models must be aligned with human values, preferencing certain continuations over…

Computation and Language · Computer Science 2024-01-02 Tsvetelina Hristova , Liam Magee , Karen Soldatic

Large reasoning models (LRMs) already possess a latent capacity for long chain-of-thought reasoning. Prior work has shown that outcome-based reinforcement learning (RL) can incidentally elicit advanced reasoning behaviors such as…

Computation and Language · Computer Science 2025-05-28 Zhiyuan Hu , Yibo Wang , Hanze Dong , Yuhui Xu , Amrita Saha , Caiming Xiong , Bryan Hooi , Junnan Li

This work studies the challenge of aligning large language models (LLMs) with offline preference data. We focus on alignment by Reinforcement Learning from Human Feedback (RLHF) in particular. While popular preference optimization methods…

Machine Learning · Computer Science 2024-06-07 Xiang Ji , Sanjeev Kulkarni , Mengdi Wang , Tengyang Xie

The multiple access channel (MAC) capacity with feedback is considered under feedback models designed to tease out which factors contribute to the MAC feedback capacity benefit. Comparing the capacity of a MAC with ``perfect'' feedback,…

Information Theory · Computer Science 2023-05-11 Oliver Kosut , Michelle Effros , Michael Langberg

AI systems in high-consequence domains such as defense, intelligence, and disaster response must detect rare, high-impact events while operating under tight resource constraints. Traditional annotation strategies that prioritize label…

Machine Learning · Computer Science 2025-05-22 Dave Cook , Tim Klawa

Large Language Models (LLMs) exhibit impressive reasoning abilities, yet their reliance on structured step-by-step processing reveals a critical limitation. In contrast, human cognition fluidly adapts between intuitive, heuristic (System 1)…

Computation and Language · Computer Science 2025-10-16 Alireza S. Ziabari , Nona Ghazizadeh , Zhivar Sourati , Farzan Karimi-Malekabadi , Payam Piray , Morteza Dehghani

In this paper, a mathematical theory of learning is proposed that has many parallels with information theory. We consider Vapnik's General Setting of Learning in which the learning process is defined to be the act of selecting a hypothesis…

Machine Learning · Computer Science 2014-05-08 Ibrahim Alabdulmohsin

This paper shows how agents' choice in communicative action can be designed to mitigate the effect of their resource limits in the context of particular features of a collaborative planning task. I first motivate a number of hypotheses…

cmp-lg · Computer Science 2008-02-03 Marilyn A. Walker

It is widely agreed that when AI models assist decision-makers in high-stakes domains by predicting an outcome of interest, they should communicate the confidence of their predictions. However, empirical evidence suggests that…

Machine Learning · Computer Science 2026-05-14 Nina Corvelo Benz , Eleni Straitouri , Manuel Gomez-Rodriguez

Every system that maintains a large language model conversation beyond a single session faces two inescapable constraints: the context window is finite, and information quality degrades with accumulated volume. We formalize these…

Computational Complexity · Computer Science 2026-04-24 Borja Odriozola Schick

Alignment in artificial intelligence pursues the consistency between model responses and human preferences as well as values. In practice, the multifaceted nature of human preferences inadvertently introduces what is known as the "alignment…

Computation and Language · Computer Science 2024-10-14 Yiju Guo , Ganqu Cui , Lifan Yuan , Ning Ding , Zexu Sun , Bowen Sun , Huimin Chen , Ruobing Xie , Jie Zhou , Yankai Lin , Zhiyuan Liu , Maosong Sun

The performance of Large Language Models (LLMs) is fundamentally determined by the contextual information provided during inference. This survey introduces Context Engineering, a formal discipline that transcends simple prompt design to…