Related papers: ROAST: Rollout-based On-distribution Activation St…

Activation steering is a promising technique for controlling LLM behavior by adding semantically meaningful vectors directly into a model's hidden states during inference. It is often framed as a precise, interpretable, and potentially…

Inference-time LLM alignment methods, particularly activation steering, offer an alternative to fine-tuning by directly modifying activations during generation. Existing methods, however, often rely on non-anticipative interventions that…

Multimodal Large Language Models (MLLMs) often exhibit significant modality preference, which is a tendency to favor one modality over another. Depending on the input, they may over-rely on linguistic priors relative to visual evidence, or…

Self-training approach for large language models (LLMs) improves reasoning abilities by training the models on their self-generated rationales. Previous approaches have labeled rationales that produce correct answers for a given question as…

Instruction tuning has recently been recognized as an effective way of aligning Large Language Models (LLMs) to enhance their generalization ability across various tasks. However, when tuning publicly accessible, centralized LLMs with…

Despite strong multi-task pretraining, existing policies often exhibit poor task steerability. For example, a robot may fail to respond to a new instruction ``put the bowl in the sink" when moving towards the oven, executing ``close the…

The internalization of chain-of-thought processes into hidden states has emerged as a highly efficient paradigm for scaling test-time compute. However, existing activation steering methods rely on static control vectors that fail to adapt…

Urban spatio-temporal (ST) forecasting is crucial for various urban applications such as intelligent scheduling and trip planning. Previous studies focus on modeling ST correlations among urban locations in offline settings, which often…

Model steering represents a powerful technique that dynamically aligns large language models (LLMs) with human preferences during inference. However, conventional model-steering methods rely heavily on externally annotated data, not only…

A key challenge in AI alignment is guiding large language models (LLMs) to follow desired behaviors at test time. Activation steering, which modifies internal model activations during inference, offers a potential solution. However, prior…

Given a textual passage and an answer, humans are able to ask questions with various expressions, but this ability is still challenging for most question generation (QG) systems. Existing solutions mainly focus on the internal knowledge…

Steering, or direct manipulation of internal activations to guide LLM responses toward specific semantic concepts, is emerging as a promising avenue for both understanding how semantic concepts are stored within LLMs and advancing LLM…

To train machine learning models that are robust to distribution shifts in the data, distributionally robust optimization (DRO) has been proven very effective. However, the existing approaches to learning a distributionally robust model…

This work examines whether activating latent subspaces in language models (LLMs) can steer scientific code generation toward a specific programming language. Five causal LLMs were first evaluated on scientific coding prompts to quantify…

We propose SLOT (Sample-specific Language Model Optimization at Test-time), a novel and parameter-efficient test-time inference approach that enhances a language model's ability to more accurately respond to individual prompts. Existing…

The reliable deployment of deep reinforcement learning in real-world settings requires the ability to generalize across a variety of conditions, including both in-distribution scenarios seen during training as well as novel…

Large language models (LLMs) demonstrate strong chain-of-thought (CoT) reasoning abilities, while smaller models (<= 3B parameters) significantly underperform on multi-step reasoning tasks. Based on empirical analyses of the Qwen-2.5 model…

Global pooling is one of the most significant operations in many machine learning models and tasks, which works for information fusion and structured data (like sets and graphs) representation. However, without solid mathematical…

Chain-of-Thought (CoT) reasoning has significantly advanced Large Language Models (LLMs) in solving complex tasks. However, its autoregressive paradigm leads to significant computational overhead, hindering its deployment in…

Recent advances in Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in solving complex tasks such as mathematics and coding. However, these models frequently exhibit a phenomenon known as overthinking during…