Despite their impressive performance, large language models (LLMs) such as ChatGPT are known to pose important risks. One such set of risks arises from misplaced confidence, whether over-confidence or under-confidence, that the models have in their inference. While the former is well studied, the latter is not, leading to an asymmetry in understanding the comprehensive risk of the model based on misplaced confidence. In this paper, we address this asymmetry by defining two types of risk (decision and composite risk), and proposing an experimental framework consisting of a two-level inference architecture and appropriate metrics for measuring such risks in both discriminative and generative LLMs. The first level relies on a decision rule that determines whether the underlying language model should abstain from inference. The second level (which applies if the model does not abstain) is the model's inference. Detailed experiments on four natural language commonsense reasoning datasets using both an open-source ensemble-based RoBERTa model and ChatGPT, demonstrate the practical utility of the evaluation framework. For example, our results show that our framework can get an LLM to confidently respond to an extra 20.1% of low-risk inference tasks that other methods might misclassify as high-risk, and skip 19.8% of high-risk tasks, which would have been answered incorrectly.

The use of large language models (LLMs) is expanding rapidly, and open-source versions are becoming available, offering users safer and more adaptable options. These models enable users to protect data privacy by eliminating the need to provide data to third parties and can be customized for specific tasks. In this study, we compare the performance of various language models on the Sustainable Development Goal (SDG) mapping task, using the output of GPT-4o as the baseline. The selected open-source models for comparison include Mixtral, LLaMA 2, LLaMA 3, Gemma, and Qwen2. Additionally, GPT-4o-mini, a more specialized version of GPT-4o, was included to extend the comparison. Given the multi-label nature of the SDG mapping task, we employed metrics such as F1 score, precision, and recall with micro-averaging to evaluate different aspects of the models' performance. These metrics are derived from the confusion matrix to ensure a comprehensive evaluation. We provide a clear observation and analysis of each model's performance by plotting curves based on F1 score, precision, and recall at different thresholds. According to the results of this experiment, LLaMA 2 and Gemma still have significant room for improvement. The other four models do not exhibit particularly large differences in performance. The outputs from all seven models are available on Zenodo: https://doi.org/10.5281/zenodo.12789375.

As NLP models become increasingly integral to decision-making processes, the need for explainability and interpretability has become paramount. In this work, we propose a framework that achieves the aforementioned by generating semantically edited inputs, known as counterfactual interventions, which change the model prediction, thus providing a form of counterfactual explanations for the model. We test our framework on two NLP tasks - binary sentiment classification and topic classification - and show that the generated edits are contrastive, fluent and minimal, while the whole process remains significantly faster that other state-of-the-art counterfactual editors.

Missing data in tabular dataset is a common issue as the performance of downstream tasks usually depends on the completeness of the training dataset. Previous missing data imputation methods focus on numeric and categorical columns, but we propose a novel end-to-end approach called Table Transformers for Imputing Textual Attributes (TTITA) based on the transformer to impute unstructured textual columns using other columns in the table. We conduct extensive experiments on two Amazon Reviews datasets, and our approach shows competitive performance outperforming baseline models such as recurrent neural networks and Llama2. The performance improvement is more significant when the target sequence has a longer length. Additionally, we incorporated multi-task learning to simultaneously impute for heterogeneous columns, boosting the performance for text imputation. We also qualitatively compare with ChatGPT for realistic applications.

The 1st Workshop on Data Contamination (CONDA 2024) focuses on all relevant aspects of data contamination in natural language processing, where data contamination is understood as situations where evaluation data is included in pre-training corpora used to train large scale models, compromising evaluation results. The workshop fostered a shared task to collect evidence on data contamination in current available datasets and models. The goal of the shared task and associated database is to assist the community in understanding the extent of the problem and to assist researchers in avoiding reporting evaluation results on known contaminated resources. The shared task provides a structured, centralized public database for the collection of contamination evidence, open to contributions from the community via GitHub pool requests. This first compilation paper is based on 566 reported entries over 91 contaminated sources from a total of 23 contributors. The details of the individual contamination events are available in the platform. The platform continues to be online, open to contributions from the community.

In this paper, we attempt to summarize monthly reports as investment reports. Fund managers have a wide range of tasks, one of which is the preparation of investment reports. In addition to preparing monthly reports on fund management, fund managers prepare management reports that summarize these monthly reports every six months or once a year. The preparation of fund reports is a labor-intensive and time-consuming task. Therefore, in this paper, we tackle investment summarization from monthly reports using transformer-based models. There are two main types of summarization methods: extractive summarization and abstractive summarization, and this study constructs both methods and examines which is more useful in summarizing investment reports.

Identifying risky driving behavior in real-world situations is essential for the safety of both drivers and pedestrians. However, integrating natural language models in this field remains relatively untapped. To address this, we created a novel multi-modal instruction tuning dataset and driver coaching inference system. Our primary use case is dashcam-based coaching for commercial drivers. The North American Dashcam Market is expected to register a CAGR of 15.4 percent from 2022 to 2027. Our dataset enables language models to learn visual instructions across various risky driving scenarios, emphasizing detailed reasoning crucial for effective driver coaching and managerial comprehension. Our model is trained on roadfacing and driver-facing RGB camera footage, capturing the comprehensive scope of driving Figure 1: Overview of our targeting coaching task.

Existing symbolic music generation methods usually utilize discriminator to improve the quality of generated music via global perception of music. However, considering the complexity of information in music, such as rhythm and melody, a single discriminator cannot fully reflect the differences in these two primary dimensions of music. In this work, we propose to decouple the melody and rhythm from music, and design corresponding fine-grained discriminators to tackle the aforementioned issues. Specifically, equipped with a pitch augmentation strategy, the melody discriminator discerns the melody variations presented by the generated samples. By contrast, the rhythm discriminator, enhanced with bar-level relative positional encoding, focuses on the velocity of generated notes. Such a design allows the generator to be more explicitly aware of which aspects should be adjusted in the generated music, making it easier to mimic human-composed music. Experimental results on the POP909 benchmark demonstrate the favorable performance of the proposed method compared to several state-of-the-art methods in terms of both objective and subjective metrics.

GAN-based image editing task aims at manipulating image attributes in the latent space of generative models. Most of the previous 2D and 3D-aware approaches mainly focus on editing attributes in images with ambiguous semantics or regions from a reference image, which fail to achieve photographic semantic attribute transfer, such as the beard from a photo of a man. In this paper, we propose an image-driven Semantic Attribute Transfer method in 3D (SAT3D) by editing semantic attributes from a reference image. For the proposed method, the exploration is conducted in the style space of a pre-trained 3D-aware StyleGAN-based generator by learning the correlations between semantic attributes and style code channels. For guidance, we associate each attribute with a set of phrase-based descriptor groups, and develop a Quantitative Measurement Module (QMM) to quantitatively describe the attribute characteristics in images based on descriptor groups, which leverages the image-text comprehension capability of CLIP. During the training process, the QMM is incorporated into attribute losses to calculate attribute similarity between images, guiding target semantic transferring and irrelevant semantics preserving. We present our 3D-aware attribute transfer results across multiple domains and also conduct comparisons with classical 2D image editing methods, demonstrating the effectiveness and customizability of our SAT3D.

As large language models (LLMs) evolve, the increase in model depth and parameter number leads to substantial redundancy. To enhance the efficiency of the attention mechanism, previous works primarily compress the KV cache or group attention heads, while largely overlooking redundancy between layers. Our comprehensive analyses across various LLMs show that highly similar attention patterns persist within most layers. It's intuitive to save the computation by sharing attention weights across layers. However, further analysis reveals two challenges: (1) Directly sharing the weight matrix without carefully rearranging the attention heads proves to be ineffective; (2) Shallow layers are vulnerable to small deviations in attention weights. Driven by these insights, we introduce LiSA, a lightweight substitute for self-attention in well-trained LLMs. LiSA employs tiny feed-forward networks to align attention heads between adjacent layers and low-rank matrices to approximate differences in layer-wise attention weights. Evaluations encompassing 13 typical benchmarks demonstrate that LiSA maintains high response quality in terms of accuracy and perplexity while reducing redundant attention calculations within 53-84% of the total layers. Our implementations of LiSA achieve a 6X compression of Q and K, with maximum throughput improvements of 19.5% for LLaMA3-8B and 32.3% for LLaMA2-7B.