AI alignment
Conformance of AI to intended objectives
📊 Rating
24 news mentions · 👍 0 likes · 👎 0 dislikes
📌 Topics
- AI Ethics (7)
- AI Safety (6)
- AI Alignment (5)
- Machine Learning (3)
- Causal Inference (2)
- Reward Modeling (2)
- AI alignment (2)
- Model Testing (1)
- Language Models (1)
- Model Analysis (1)
- Political Bias (1)
- Human-AI Interaction (1)
🏷️ Keywords
AI alignment (23) · large language models (6) · reward modeling (3) · reinforcement learning (3) · AI safety (3) · ethical dilemmas (2) · safety (2) · reward hacking (2) · interpretability (2) · Large language models (2) · adversarial testing (1) · moral reasoning (1) · stress testing (1) · vulnerabilities (1) · language models (1) · ethical instructions (1) · deliberation (1) · consistency (1) · other-recognition (1) · ethical frameworks (1)
📖 Key Information
📰 Related News (24)
-
🇺🇸 Adversarial Moral Stress Testing of Large Language Models
arXiv:2604.01108v1 Announce Type: new Abstract: Evaluating the ethical robustness of large language models (LLMs) deployed in software systems remain...
-
🇺🇸 How Do Language Models Process Ethical Instructions? Deliberation, Consistency, and Other-Recognition Across Four Models
arXiv:2604.00021v1 Announce Type: cross Abstract: Alignment safety research assumes that ethical instructions improve model behavior, but how languag...
-
🇺🇸 Probing Ethical Framework Representations in Large Language Models: Structure, Entanglement, and Methodological Challenges
arXiv:2603.23659v1 Announce Type: cross Abstract: When large language models make ethical judgments, do their internal representations distinguish be...
-
🇺🇸 PoliticsBench: Benchmarking Political Values in Large Language Models with Multi-Turn Roleplay
arXiv:2603.23841v1 Announce Type: cross Abstract: While Large Language Models (LLMs) are increasingly used as primary sources of information, their p...
-
🇺🇸 Multi-Trait Subspace Steering to Reveal the Dark Side of Human-AI Interaction
arXiv:2603.18085v1 Announce Type: new Abstract: Recent incidents have highlighted alarming cases where human-AI interactions led to negative psycholo...
-
🇺🇸 TherapyGym: Evaluating and Aligning Clinical Fidelity and Safety in Therapy Chatbots
arXiv:2603.18008v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for mental-health support; yet prevailing evalua...
-
🇺🇸 CausalRM: Causal-Theoretic Reward Modeling for RLHF from Observational User Feedbacks
arXiv:2603.18736v1 Announce Type: cross Abstract: Despite the success of reinforcement learning from human feedback (RLHF) in aligning language model...
-
🇺🇸 Prompt Programming for Cultural Bias and Alignment of Large Language Models
arXiv:2603.16827v1 Announce Type: new Abstract: Culture shapes reasoning, values, prioritization, and strategic decision-making, yet large language m...
-
🇺🇸 MetaKE: Meta-learning Aligned Knowledge Editing via Bi-level Optimization
arXiv:2603.12677v1 Announce Type: cross Abstract: Knowledge editing (KE) aims to precisely rectify specific knowledge in Large Language Models (LLMs)...
-
🇺🇸 Aligning Large Language Model Agents with Rational and Moral Preferences: A Supervised Fine-Tuning Approach
arXiv:2507.20796v2 Announce Type: replace-cross Abstract: As large language models (LLMs) increasingly act as autonomous agents in markets and organi...
-
🇺🇸 Safe RLHF Beyond Expectation: Stochastic Dominance for Universal Spectral Risk Control
arXiv:2603.10938v1 Announce Type: cross Abstract: Safe Reinforcement Learning from Human Feedback (RLHF) typically enforces safety through expected c...
-
🇺🇸 Countdown-Code: A Testbed for Studying The Emergence and Generalization of Reward Hacking in RLVR
arXiv:2603.07084v1 Announce Type: cross Abstract: Reward hacking is a form of misalignment in which models overoptimize proxy rewards without genuine...
-
🇺🇸 CDRRM: Contrast-Driven Rubric Generation for Reliable and Interpretable Reward Modeling
arXiv:2603.08035v1 Announce Type: new Abstract: Reward modeling is essential for aligning Large Language Models(LLMs) with human preferences, yet con...
-
🇺🇸 RM-R1: Reward Modeling as Reasoning
arXiv:2505.02387v4 Announce Type: replace-cross Abstract: Reward modeling is essential for aligning large language models with human preferences thro...
-
🇺🇸 Causally Robust Reward Learning from Reason-Augmented Preference Feedback
arXiv:2603.04861v1 Announce Type: new Abstract: Preference-based reward learning is widely used for shaping agent behavior to match a user's preferen...
-
🇺🇸 Semantic Containment as a Fundamental Property of Emergent Misalignment
arXiv:2603.04407v1 Announce Type: cross Abstract: Fine-tuning language models on narrowly harmful data causes emergent misalignment (EM) -- behaviora...
-
🇺🇸 DARE: Aligning LLM Agents with the R Statistical Ecosystem via Distribution-Aware Retrieval
arXiv:2603.04743v1 Announce Type: cross Abstract: Large Language Model (LLM) agents can automate data-science workflows, but many rigorous statistica...
-
🇺🇸 VISA: Value Injection via Shielded Adaptation for Personalized LLM Alignment
arXiv:2603.04822v1 Announce Type: new Abstract: Aligning Large Language Models (LLMs) with nuanced human values remains a critical challenge, as exis...
-
🇺🇸 Asymmetric Goal Drift in Coding Agents Under Value Conflict
arXiv:2603.03456v1 Announce Type: new Abstract: Agentic coding agents are increasingly deployed autonomously, at scale, and over long-context horizon...
-
🇺🇸 Training Agents to Self-Report Misbehavior
arXiv:2602.22303v1 Announce Type: cross Abstract: Frontier AI agents may pursue hidden goals while concealing their pursuit from oversight. Alignment...
-
🇺🇸 CAMEL: Confidence-Gated Reflection for Reward Modeling
arXiv:2602.20670v1 Announce Type: cross Abstract: Reward models play a fundamental role in aligning large language models with human preferences. Exi...
-
🇺🇸 PromptCD: Test-Time Behavior Enhancement via Polarity-Prompt Contrastive Decoding
arXiv:2602.20696v1 Announce Type: new Abstract: Reliable AI systems require large language models (LLMs) to exhibit behaviors aligned with human pref...
-
🇺🇸 Advancing independent research on AI alignment
OpenAI commits $7.5M to The Alignment Project to fund independent AI alignment research, strengthening global efforts to address AGI safety and securi...
-
🇺🇸 Curriculum-DPO++: Direct Preference Optimization via Data and Model Curricula for Text-to-Image Generation
arXiv:2602.13055v1 Announce Type: cross Abstract: Direct Preference Optimization (DPO) has been proposed as an effective and efficient alternative to...
🔗 Entity Intersection Graph
People and organizations frequently mentioned alongside AI alignment:
-
🌐
Large language model · 7 shared articles
-
🌐
AI safety · 3 shared articles
-
Reinforcement learning from human feedback · 2 shared articles -
🌐
Cultural bias · 1 shared articles
-
OpenAI · 1 shared articles -
🌐
Stochastic dominance · 1 shared articles
-
Generative artificial intelligence · 1 shared articles -
Visa Inc. · 1 shared articles -
🌐
Machine learning · 1 shared articles
-
🌐
Dare · 1 shared articles