English
Related papers

Related papers: Deliberative Alignment: Reasoning Enables Safer La…

200 papers

Large Language Models (LLMs) are increasingly employed in software engineering tasks such as requirements elicitation, design, and evaluation, raising critical questions regarding their alignment with human judgments on responsible AI…

Software Engineering · Computer Science 2025-11-07 Asma Yamani , Malak Baslyman , Moataz Ahmed

Social alignment in AI systems aims to ensure that these models behave according to established societal values. However, unlike humans, who derive consensus on value judgments through social interaction, current language models (LMs) are…

Computation and Language · Computer Science 2023-10-31 Ruibo Liu , Ruixin Yang , Chenyan Jia , Ge Zhang , Denny Zhou , Andrew M. Dai , Diyi Yang , Soroush Vosoughi

Natural language reasoning plays an increasingly important role in improving language models' ability to solve complex language understanding tasks. An interesting use case for reasoning is the resolution of context-dependent ambiguity. But…

Computation and Language · Computer Science 2023-10-24 Stefan F. Schouten , Peter Bloem , Ilia Markov , Piek Vossen

Achieving human-like reasoning capabilities in Multimodal Large Language Models (MLLMs) has long been a goal. Current methods primarily focus on synthesizing positive rationales, typically relying on manual annotations or complex systems.…

Computation and Language · Computer Science 2025-07-29 Wentao Tan , Qiong Cao , Yibing Zhan , Chao Xue , Changxing Ding

Large-scale foundation models exhibit \emph{behavioral shifts} when subjected to interventions such as scaling, fine-tuning, reinforcement learning with human feedback, or in-context learning. Current explainability methods are structurally…

Artificial Intelligence · Computer Science 2026-05-21 Martino Ciaperoni , Marzio Di Vece , Roberto Pellungrini , Luca Pappalardo , Fosca Giannotti , Francesco Giannini

Aligning language models for both helpfulness and safety typically requires complex pipelines-separate reward and cost models, online reinforcement learning, and primal-dual updates. Recent direct preference optimization approaches simplify…

Machine Learning · Computer Science 2026-05-13 Tien-Phat Nguyen , Truong Nguyen , Thin Nguyen , Duy Minh Ho Nguyen , Ngoc-Thanh Dinh , Trung Le

Enhancing the reasoning capabilities of language models (LMs) remains a key challenge, especially for tasks that require complex, multi-step decision-making where existing Chain-of-Thought (CoT) approaches struggle with consistency and…

Computation and Language · Computer Science 2025-08-21 Siheng Xiong , Ali Payani , Yuan Yang , Faramarz Fekri

The safety of large language models (LLMs) has increasingly emerged as a fundamental aspect of their development. Existing safety alignment for LLMs is predominantly achieved through post-training methods, which are computationally…

Artificial Intelligence · Computer Science 2026-02-03 Sicheng Shen , Mingyang Lv , Han Shen , Jialin Wu , Binghao Wang , Zhou Yang , Guobin Shen , Dongcheng Zhao , Feifei Zhao , Yi Zeng

Large Language Models (LLMs) have enabled the development of powerful agentic systems capable of automating complex workflows across various fields. However, these systems are highly vulnerable to indirect prompt injection attacks, where…

Cryptography and Security · Computer Science 2026-01-16 Hao Li , Yankai Yang , G. Edward Suh , Ning Zhang , Chaowei Xiao

Open-weight advanced AI models -- systems whose parameters are freely available for download and adaptation -- are reshaping the global AI landscape. As these models rapidly close the performance gap with closed alternatives, they enable…

Computers and Society · Computer Science 2026-02-24 Bengüsu Özcan , Alex Petropoulos , Max Reddel

Currently OpenAI o1 sparks a surge of interest in the study of large reasoning models (LRM). Building on this momentum, Marco-o1 not only focuses on disciplines with standard answers, such as mathematics, physics, and coding -- which are…

Computation and Language · Computer Science 2024-11-26 Yu Zhao , Huifeng Yin , Bo Zeng , Hao Wang , Tianqi Shi , Chenyang Lyu , Longyue Wang , Weihua Luo , Kaifu Zhang

Sequential recommender systems have become increasingly important in real-world applications that model user behavior sequences to predict their preferences. However, existing sequential recommendation methods predominantly rely on…

Information Retrieval · Computer Science 2025-06-05 Enze Liu , Bowen Zheng , Xiaolei Wang , Wayne Xin Zhao , Jinpeng Wang , Sheng Chen , Ji-Rong Wen

Opinion modeling aims to capture individual or group political preferences, enabling applications such as digital democracies, where models could help shape fairer and more popular policies. Given their versatility, strong generalization…

Computation and Language · Computer Science 2026-03-13 Frédéric Berdoz , Yann Billeter , Yann Vonlanthen , Roger Wattenhofer

Language models have been shown to perform remarkably well on a wide range of natural language processing tasks. In this paper, we propose LEAP, a novel system that uses language models to perform multi-step logical reasoning and…

Computation and Language · Computer Science 2023-11-08 Hongyu Zhao , Kangrui Wang , Mo Yu , Hongyuan Mei

Normative reasoning is a type of reasoning that involves normative or deontic modality, such as obligation and permission. While large language models (LLMs) have demonstrated remarkable performance across various reasoning tasks, their…

Artificial Intelligence · Computer Science 2025-11-03 Kentaro Ozeki , Risako Ando , Takanobu Morishita , Hirohiko Abe , Koji Mineshima , Mitsuhiro Okada

Recent advances in Large Language Models (LLMs) highlight the need to align their behaviors with human values. A critical, yet understudied, issue is the potential divergence between an LLM's stated preferences (its reported alignment with…

Artificial Intelligence · Computer Science 2025-06-03 Zhuojun Gu , Quan Wang , Shuchu Han

Legal Artificial Intelligence (LegalAI) has achieved notable advances in automating judicial decision-making with the support of Large Language Models (LLMs). However, existing legal LLMs still struggle to generate reliable and…

Computation and Language · Computer Science 2026-02-10 Xin Dai , Buqiang Xu , Zhenghao Liu , Yukun Yan , Huiyuan Xie , Xiaoyuan Yi , Shuo Wang , Ge Yu

As large language model (LLM) based systems take on high-stakes roles in real-world decision-making, they must reconcile competing instructions from multiple sources (e.g., model developers, users, and tools) within a single prompt context.…

Computation and Language · Computer Science 2026-02-19 Zishuo Zheng , Vidhisha Balachandran , Chan Young Park , Faeze Brahman , Sachin Kumar

Case-based reasoning networks are machine-learning models that make predictions based on similarity between the input and prototypical parts of training samples, called prototypes. Such models are able to explain each decision by pointing…

Artificial Intelligence · Computer Science 2025-11-21 Jules Soria , Zakaria Chihani , Julien Girard-Satabin , Alban Grastien , Romain Xu-Darme , Daniela Cancila

Safely aligning large language models (LLMs) often demands extensive human-labeled preference data, a process that's both costly and time-consuming. While synthetic data offers a promising alternative, current methods frequently rely on…

Cryptography and Security · Computer Science 2025-06-13 Kyubyung Chae , Hyunbin Jin , Taesup Kim