English
Related papers

Related papers: How Do Language Models Process Ethical Instruction…

200 papers

Controlling the behavior of large language models (LLMs) at inference time is essential for aligning outputs with human abilities and safety requirements. \emph{Activation steering} provides a lightweight alternative to prompt engineering…

Artificial Intelligence · Computer Science 2026-01-30 Diaoulé Diallo , Katharina Dworatzyk , Sophie Jentzsch , Peer Schütt , Sabine Theis , Tobias Hecking

Alignment of the language model with human preferences is a common approach to making a language model useful to end users. However, most alignment work is done in English, and human preference datasets are dominated by English, reflecting…

Computation and Language · Computer Science 2024-06-25 Yuu Jinnai

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

Is it possible to use natural language to intervene in a model's behavior and alter its prediction in a desired way? We investigate the effectiveness of natural language interventions for reading-comprehension systems, studying this in the…

Computation and Language · Computer Science 2021-06-04 Jieyu Zhao , Daniel Khashabi , Tushar Khot , Ashish Sabharwal , Kai-Wei Chang

We show that language models' activations linearly encode when information was learned during training. Our setup involves creating a model with a known training order by sequentially fine-tuning Llama-3.2-1B on six disjoint but otherwise…

Machine Learning · Computer Science 2025-09-23 Dmitrii Krasheninnikov , Richard E. Turner , David Krueger

We investigate empathy-in-action -- the willingness to sacrifice task efficiency to address human needs -- as a linear direction in LLM activation space. Using contrastive prompts grounded in the Empathy-in-Action (EIA) benchmark, we test…

Computation and Language · Computer Science 2025-11-24 Juan P. Cadile

Large Language Models (LLMs) are increasingly deployed to automatically label and analyze educational dialogue at scale, yet current pipelines lack reliable ways to detect when models are wrong. We investigate whether reasoning generated by…

Computation and Language · Computer Science 2026-02-11 Bakhtawar Ahtisham , Kirk Vanacore , Zhuqian Zhou , Jinsook Lee , Rene F. Kizilcec

Large language models (LLMs) with instruction fine-tuning demonstrate superior generative capabilities. However, these models are resource-intensive. To alleviate this issue, we explore distilling knowledge from instruction-tuned LLMs into…

Computation and Language · Computer Science 2024-01-30 Minghao Wu , Abdul Waheed , Chiyu Zhang , Muhammad Abdul-Mageed , Alham Fikri Aji

Safety fine-tuning helps align Large Language Models (LLMs) with human preferences for their safe deployment. To better understand the underlying factors that make models safe via safety fine-tuning, we design a synthetic data generation…

Machine Learning · Computer Science 2024-08-22 Samyak Jain , Ekdeep Singh Lubana , Kemal Oksuz , Tom Joy , Philip H. S. Torr , Amartya Sanyal , Puneet K. Dokania

We explore how large language models (LLMs) can be influenced by prompting them to alter their initial decisions and align them with established ethical frameworks. Our study is based on two experiments designed to assess the susceptibility…

Computation and Language · Computer Science 2024-11-19 Allison Huang , Yulu Niki Pi , Carlos Mougan

LLMs have achieved remarkable success in complex reasoning tasks, yet current evaluation approaches predominantly rely on final-answer correctness, offering limited insight into the underlying reasoning processes that produce those answers.…

Artificial Intelligence · Computer Science 2026-05-26 Ali Şenol , Garima Agrawal , Huan Liu

Despite the significant improvements achieved by large language models (LLMs) in English reasoning tasks, these models continue to struggle with multilingual reasoning. Recent studies leverage a full-parameter and two-stage training…

Computation and Language · Computer Science 2025-01-08 Yuchun Fan , Yongyu Mu , Yilin Wang , Lei Huang , Junhao Ruan , Bei Li , Tong Xiao , Shujian Huang , Xiaocheng Feng , Jingbo Zhu

While the wide adoption of refusal training in large language models (LLMs) has showcased improvements in model safety, recent works have highlighted shortcomings due to the shallow nature of these alignment methods. To this end, the work…

Machine Learning · Computer Science 2026-04-17 Pankayaraj Pathmanathan , Furong Huang

As Large Language Models (LLMs) are deployed with increasing real-world responsibilities, it is important to be able to specify and constrain the behavior of these systems in a reliable manner. Model developers may wish to set explicit…

Artificial Intelligence · Computer Science 2024-03-11 Norman Mu , Sarah Chen , Zifan Wang , Sizhe Chen , David Karamardian , Lulwa Aljeraisy , Basel Alomair , Dan Hendrycks , David Wagner

Small language models (SLMs) in the 100M-10B parameter range increasingly power production systems, yet whether they possess the internal emotion representations recently discovered in frontier models remains unknown. We present the first…

Computation and Language · Computer Science 2026-04-07 Jihoon Jeong

Many applications of large language models (LLMs) require deductive reasoning, yet models frequently produce incorrect or redundant inference steps. We frame natural language inference as a search problem where the final answer is the valid…

Artificial Intelligence · Computer Science 2026-05-26 Andreas Opedal , Francesco Ignazio Re , Abulhair Saparov , Mrinmaya Sachan , Bernhard Schölkopf , Ryan Cotterell

Large language models (LLMs) are increasingly applied in diverse real-world scenarios, each governed by bespoke behavioral and safety specifications (spec) custom-tailored by users or organizations. These spec, categorized into safety-spec…

Computation and Language · Computer Science 2025-10-07 Haoran Zhang , Yafu Li , Xuyang Hu , Dongrui Liu , Zhilin Wang , Bo Li , Yu Cheng

Large language models (LLMs) and their variants have shown extraordinary efficacy across numerous downstream natural language processing (NLP) tasks, which has presented a new vision for the development of NLP. Despite their remarkable…

Computation and Language · Computer Science 2024-01-18 Yazhou Zhang , Mengyao Wang , Youxi Wu , Prayag Tiwari , Qiuchi Li , Benyou Wang , Jing Qin

Large language models often display heterogeneous moral preferences across settings. We study inference-time steering toward a desired ethical framework while preserving general competence. We present Convergent-Divergent Routing, which…

Artificial Intelligence · Computer Science 2026-05-06 Chenchen Yuan , Zheyu Zhang , Gjergji Kasneci

Do We Need Role Models? How do Role Models Shape Collective Morality? To explore the questions, we build a multi-agent simulation powered by a Large Language Model, where agents with diverse intrinsic drives, ranging from cooperative to…

Multiagent Systems · Computer Science 2026-03-17 Junjie Liao , Huacong Tang , Zhou Ziheng , Yizhou Wang , Fangwei Zhong
‹ Prev 1 8 9 10 Next ›