Related papers: Enhancing Training Data Attribution for Large Lang…
A critical aspect of analyzing and improving modern machine learning systems lies in understanding how individual training examples influence a model's predictive behavior. Estimating this influence enables critical applications, including…
We explore the internal mechanisms of how bias emerges in large language models (LLMs) when provided with ambiguous comparative prompts: inputs that compare or enforce choosing between two or more entities without providing clear context…
While large language models (LLMs) are extensively used, there are raising concerns regarding privacy, security, and copyright due to their opaque training data, which brings the problem of detecting pre-training data on the table. Current…
Large language models (LLMs) exhibit social biases that reinforce harmful stereotypes, limiting their safe deployment. Most existing debiasing methods adopt a suppressive paradigm by modifying parameters, prompts, or neurons associated with…
Preference alignment in Large Language Models (LLMs) has significantly improved their ability to adhere to human instructions and intentions. However, existing direct alignment algorithms primarily focus on relative preferences and often…
In online advertising, users may be exposed to a range of different advertising campaigns, such as natural search or referral or organic search, before leading to a final transaction. Estimating the contribution of advertising campaigns on…
The increasing demand for long-context modeling in large language models (LLMs) is bottlenecked by the quadratic complexity of the standard self-attention mechanism. The community has proposed sparse attention to mitigate this issue.…
In the realms of computer vision and natural language processing, Multimodal Large Language Models (MLLMs) have become indispensable tools, proficient in generating textual responses based on visual inputs. Despite their advancements, our…
Gender bias exists in natural language datasets which neural language models tend to learn, resulting in biased text generation. In this research, we propose a debiasing approach based on the loss function modification. We introduce a new…
Sentiment analysis plays a crucial role in various domains, such as business intelligence and financial forecasting. Large language models (LLMs) have become a popular paradigm for sentiment analysis, leveraging multi-task learning to…
Speculative decoding accelerates large language model (LLM) inference by using a small draft model to generate candidate tokens for a larger target model to verify. The efficacy of this technique hinges on the trade-off between the time…
Visual reinforcement learning agents typically face serious performance declines in real-world applications caused by visual distractions. Existing methods rely on fine-tuning the policy's representations with hand-crafted augmentations. In…
Biases in the dataset often enable the model to achieve high performance on in-distribution data, while poorly performing on out-of-distribution data. To mitigate the detrimental effect of the bias on the networks, previous works have…
With the development of deep learning, the field of face anti-spoofing (FAS) has witnessed great progress. FAS is usually considered a classification problem, where each class is assumed to contain a single cluster optimized by softmax…
It is widely recognized that deep neural networks are sensitive to bias in the data. This means that during training these models are likely to learn spurious correlations between data and labels, resulting in limited generalization…
Large language models (LLMs) have shown remarkable capability in numerous tasks and applications. However, fine-tuning LLMs using high-quality datasets under external supervision remains prohibitively expensive. In response, LLM…
Despite their impressive capabilities, large language models (LLMs) have been observed to generate responses that include inaccurate or fabricated information, a phenomenon commonly known as ``hallucination''. In this work, we propose a…
Text-based Person Retrieval (TPR) aims to retrieve person images that match the description given a text query. The performance improvement of the TPR model relies on high-quality data for supervised training. However, it is difficult to…
Although Large Language Models (LLMs) are showing impressive performance on a wide range of Natural Language Processing tasks, researchers have found that they still have limited ability to conduct induction. Recent works mainly adopt…
As one of the most fundamental models, meta learning aims to effectively address few-shot learning challenges. However, it still faces significant issues related to the training data, such as training inefficiencies due to numerous…