Related papers: Adaptive Activation Steering: A Tuning-Free LLM Tr…
Large Vision-Language Models (LVLMs) exhibit outstanding performance on vision-language tasks but struggle with hallucination problems. Through in-depth analysis of LVLM activation patterns, we reveal two key findings: 1) truthfulness and…
Large language models (LLMs), optimized through human feedback, have rapidly emerged as a leading paradigm for developing intelligent conversational assistants. However, despite their strong performance across many benchmarks, LLM-based…
Large Vision-Language Models (LVLMs) frequently suffer from severe hallucination issues. Existing mitigation strategies predominantly rely on isolated, single-step states to enhance visual focus or suppress strong linguistic priors.…
Attention is a fundamental component behind the remarkable achievements of large language models (LLMs). However, our current understanding of the attention mechanism, especially regarding how attention distributions are established,…
Recent work on activation and latent steering has demonstrated that modifying internal representations can effectively guide large language models (LLMs) toward improved reasoning and efficiency without additional training. However, most…
Large Language Models (LLMs) sometimes suffer from producing hallucinations, especially LLMs may generate untruthful responses despite knowing the correct knowledge. Activating the truthfulness within LLM is the key to fully unlocking LLM's…
Training large language models (LLMs) as autonomous agents often begins with imitation learning, but it only teaches agents what to do without understanding why: agents never contrast successful actions against suboptimal alternatives and…
Alignment is a standard procedure to fine-tune pre-trained large language models (LLMs) to follow natural language instructions and serve as helpful AI assistants. We have observed, however, that the conventional alignment process fails to…
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…
As large language models (LLMs) become more integrated into societal systems, the risk of them perpetuating and amplifying harmful biases becomes a critical safety concern. Traditional methods for mitigating bias often rely on data…
Large Audio-Language Models and Multi-Modal Large Language Models have demonstrated strong capabilities in tasks such as Audio Question Answering (AQA), Audio Captioning, and Automatic Speech Recognition (ASR). However, there is growing…
Large language models (LLMs) can generate long-form and coherent text, yet they often hallucinate facts, which undermines their reliability. To mitigate this issue, inference-time methods steer LLM representations toward the "truthful…
The increasing capabilities of large generative models and their ever more widespread deployment have raised concerns about their reliability, safety, and potential misuse. To address these issues, recent works have proposed to control…
Detecting hallucinations in Large Language Model-generated text is crucial for their safe deployment. While probing classifiers show promise, they operate on isolated layer-token pairs and are LLM-specific, limiting their effectiveness and…
Large Vision-Language Models (LVLMs) have achieved substantial progress in cross-modal tasks. However, due to language bias, LVLMs are susceptible to object hallucination, which can be primarily divided into category, attribute, and…
Large Language Models (LLMs) often generate inconsistent responses when prompted with semantically equivalent paraphrased inputs. Recently, activation steering, a technique that modulates LLMs' behaviours by adjusting their latent…
Large Language Models (LLMs) exhibit impressive capabilities but often hallucinate, confidently providing incorrect answers instead of admitting ignorance. Prior work has shown that models encode linear representations of their own…
Controlling the behavior of large language models (LLMs) at inference time is essential for aligning outputs with human abilities and safety requirements. \emph{Activation steering} provides a lightweight alternative to prompt engineering…
Large Language Models frequently generate fluent but factually incorrect text. We propose Adaptive Activation Cancellation (AAC), a real-time inference-time framework that treats hallucination-associated neural activations as structured…
Large Language Models (LLMs) frequently produce factually inaccurate outputs - a phenomenon known as hallucination - which limits their accuracy in knowledge-intensive NLP tasks. Retrieval-augmented generation and agentic frameworks such as…