相关论文: Steering LLMs for Culturally Localized Generation

Due to their architecture and vast pre-training data, large language models (LLMs) demonstrate strong text classification performance. However, LLM output - here, the category assigned to a text - depends heavily on the wording of the…

Skill discovery methods enable agents to learn diverse emergent behaviors without explicit rewards. To make learned skills useful for unknown downstream tasks, obtaining a semantically diverse repertoire of skills is essential. While some…

Recommender systems are essential for delivering personalized content across digital platforms by modeling user preferences and behaviors. Recently, large language models (LLMs) have been adopted for prompt-based recommendation due to their…

Changing the behavior of large language models (LLMs) can be as straightforward as editing the Transformer's residual streams using appropriately constructed "steering vectors." These modifications to internal neural activations, a form of…

Latent space steering methods provide a practical approach to controlling large language models by applying steering vectors to intermediate activations, guiding outputs toward desired behaviors while avoiding retraining. Despite their…

Ensuring fairness in machine learning requires understanding how sensitive attributes like race or gender causally influence outcomes. Existing causal discovery (CD) methods often struggle to recover fairness-relevant pathways in the…

As LLMs are increasingly deployed in global applications, the importance of cultural sensitivity becomes paramount, ensuring that users from diverse backgrounds feel respected and understood. Cultural harm can arise when these models fail…

Large language models (LLMs) are known to be sensitive to input phrasing, but the mechanisms by which semantic cues shape reasoning remain poorly understood. We investigate this phenomenon in the context of comparative math problems with…

Aligned representations across languages is a desired property in multilingual large language models (mLLMs), as alignment can improve performance in cross-lingual tasks. Typically alignment requires fine-tuning a model, which is…

Local Interpretable Model-Agnostic Explanations (LIME) is a popular technique used to increase the interpretability and explainability of black box Machine Learning (ML) algorithms. LIME typically generates an explanation for a single…

Training Large Language Models (LLMs) with high multilingual coverage is becoming increasingly important -- especially when monolingual resources are scarce. Recent studies have found that LLMs process multilingual inputs in shared concept…

Machine learning software is being used in many applications (finance, hiring, admissions, criminal justice) having a huge social impact. But sometimes the behavior of this software is biased and it shows discrimination based on some…

Mixture-of-Experts (MoE) architectures have shown strong multilingual capabilities, yet the internal mechanisms underlying performance gains and cross-language differences remain insufficiently understood. In this work, we conduct a…

In Large Language Models (LLMs) generation, there exist knowledge conflicts and scenarios where parametric knowledge contradicts knowledge provided in the context. Previous works studied tuning, decoding algorithms, or locating and editing…

To ensure the trustworthiness and interpretability of AI systems, it is essential to align machine learning models with human domain knowledge. This can be a challenging and time-consuming endeavor that requires close communication between…

In the current media landscape, understanding the framing of information is crucial for critical consumption and informed decision making. Framing analysis is a valuable tool for identifying the underlying perspectives used to present…

While cultural alignment has increasingly become a focal point within AI research, current approaches relying predominantly on quantitative benchmarks and simplistic proxies fail to capture the deeply nuanced and context-dependent nature of…

Research has shown that while large language models (LLMs) can generate their responses based on cultural context, they are not perfect and tend to generalize across cultures. However, when evaluating the cultural bias of a language…

We demonstrate experimental results with LLMs that address robotics task planning problems. Recently, LLMs have been applied in robotics task planning, particularly using a code generation approach that converts complex high-level…

Despite growing research on bias in large language models (LLMs), most work has focused on gender and race, with little attention to religious identity. This paper explores how religion is internally represented in LLMs and how it…