相关论文: Value-Conflict Diagnostics Reveal Widespread Align…

As foundation models grow increasingly more intelligent, reliable and trustworthy safety evaluation becomes more indispensable than ever. However, an important question arises: Whether and how an advanced AI system would perceive the…

We present a novel statistical framework for analyzing stereotypes in large language models (LLMs) by systematically estimating the bias and variation in their generation. Current alignment evaluation metrics often overlook stereotypes'…

Large Language Model (LLM) alignment aims to ensure that LLM outputs match with human values. Researchers have demonstrated the severity of alignment problems with a large spectrum of jailbreak techniques that can induce LLMs to produce…

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…

LLM alignment has progressed in single-agent settings through paradigms such as RL with human feedback (RLHF), while recent work explores scalable alternatives such as RL with AI feedback (RLAIF) and dynamic alignment objectives. However,…

Recently, large vision-language models (LVLMs) have emerged as the preferred tools for judging text-image alignment, yet their robustness along the visual modality remains underexplored. This work is the first study to address a key…

We present ALF (Advertiser Large Foundation model), a multi-modal transformer architecture for understanding advertiser behavior and intent across text, image, video, and structured data modalities. Through contrastive learning and…

Recent vision-language (VL) models are powerful, but can they reliably distinguish "right" from "left"? We curate three new corpora to quantify model comprehension of such basic spatial relations. These tests isolate spatial reasoning more…

Large language models (LLMs) can lead to undesired consequences when misaligned with human values, especially in scenarios involving complex and sensitive social biases. Previous studies have revealed the misalignment of LLMs with human…

The deployment of Large Language Models (LLMs) as tool-using agents causes their alignment training to manifest in new ways. Recent work finds that language models can use tools in ways that contradict the interests or explicit instructions…

With the rapid advancement of large language models (LLMs), aligning them with human values for safety and ethics has become a critical challenge. This problem is especially challenging when multiple, potentially conflicting human values…

Large language models (LLMs) increasingly operate in multi-agent and safety-critical settings, raising open questions about how their vulnerabilities scale when models interact adversarially. This study examines whether larger models can…

As LLMs enter conflict monitoring, understanding systematic distortions in their outputs is critical for humanitarian accountability. We evaluate four vanilla open-weight models Gemma 3 4B, Llama 3.2 3B, Mistral 7B, and OLMo 2 7B and two…

As Large Language Model (LLM) agents become more widespread, associated misalignment risks increase. While prior research has studied agents' ability to produce harmful outputs or follow malicious instructions, it remains unclear how likely…

Large language models trained under diverse objectives and architectures have been shown to develop increasingly similar internal representations, an observation formalized as the Platonic Representation Hypothesis. Whether this…

Large language model safety is usually assessed with static benchmarks, but key failures are dynamic: value drift under distribution shift, jailbreak attacks, and slow degradation of alignment in deployment. Building on a recent Second Law…

Vision-Language-Action (VLA) policies are typically deployed with asynchronous inference: the robot executes a previously predicted action chunk while the model computes the next one. This creates a prediction-execution misalignment: the…

Linearly transforming stimulus representations of deep neural networks yields high-performing models of behavioral and neural responses to complex stimuli. But does the test accuracy of such predictions identify genuine representational…

Vision-language models (VLMs) are increasingly deployed as trusted authorities -- fact-checking images on social media, comparing products, and moderating content. Users implicitly trust that these systems perceive the same visual content…

We introduce the Deep Value Benchmark (DVB), an evaluation framework that directly tests whether large language models (LLMs) learn fundamental human values or merely surface-level preferences. This distinction is critical for AI alignment:…