Data contamination in language model evaluation is increasingly prevalent as the popularity of large language models. It allows models to "cheat" via memorisation instead of displaying true capabilities. Therefore, contamination analysis has became an crucial part of reliable model evaluation to validate results. However, existing contamination analysis is usually conducted internally by LLM developers and often lacks transparency and completeness. This paper present an open source data contamination reports for the Llama series models. We analyse six popular multi-choice QA benchmarks and quantify their overlapping with the training set of Llama. Various levels of contamination ranging from 1\% to 8.7\% are found across benchmarks. Our comparison also reveals that Llama models can gain over 5\% higher accuracy on contaminated subsets versus clean subsets. Data and code are available at: https://github.com/liyucheng09/Contamination_Detector.
Large language models (LLMs) achieved remarkable performance across various tasks. However, they face challenges in managing long documents and extended conversations, due to significantly increased computational requirements, both in memory and inference time, and potential context truncation when the input exceeds the LLM's fixed context length. This paper proposes a method called Selective Context that enhances the inference efficiency of LLMs by identifying and pruning redundancy in the input context to make the input more compact. We test our approach using common data sources requiring long context processing: arXiv papers, news articles, and long conversations, on tasks of summarisation, question answering, and response generation. Experimental results show that Selective Context significantly reduces memory cost and decreases generation latency while maintaining comparable performance compared to that achieved when full context is used. Specifically, we achieve a 50\% reduction in context cost, resulting in a 36\% reduction in inference memory usage and a 32\% reduction in inference time, while observing only a minor drop of .023 in BERTscore and .038 in faithfulness on four downstream applications, indicating that our method strikes a good balance between efficiency and performance.
Data contamination in model evaluation is getting increasingly prevalent as the massive training corpora of large language models often unintentionally include benchmark samples. Therefore, contamination analysis has became an inevitable part of reliable model evaluation. However, existing method of contamination analysis requires the access of the entire training data which is often confidential for recent models. This prevent the community to rigorously audit these models and conduct accurate assessment of their capability. In this paper, we propose a novel method to quantify contamination without the access of the full training set, that measure the extent of contamination with perplexity. Our analysis provides evidence of significant memorisation of recent foundation models in popular reading comprehension, summarisation benchmarks, while multiple choice appears less contaminated.
One noticeable trend in metaphor detection is the embrace of linguistic theories such as the metaphor identification procedure (MIP) for model architecture design. While MIP clearly defines that the metaphoricity of a lexical unit is determined based on the contrast between its \textit{contextual meaning} and its \textit{basic meaning}, existing work does not strictly follow this principle, typically using the \textit{aggregated meaning} to approximate the basic meaning of target words. In this paper, we propose a novel metaphor detection method, which models the basic meaning of the word based on literal annotation from the training set, and then compares this with the contextual meaning in a target sentence to identify metaphors. Empirical results show that our method outperforms the state-of-the-art method significantly by 1.0\% in F1 score. Moreover, our performance even reaches the theoretical upper bound on the VUA18 benchmark for targets with basic annotations, which demonstrates the importance of modelling basic meanings for metaphor detection.
Large language models (LLMs) have received significant attention by achieving remarkable performance across various tasks. However, their fixed context length poses challenges when processing long documents or maintaining extended conversations. This paper proposes a method called \textit{Selective Context} that employs self-information to filter out less informative content, thereby enhancing the efficiency of the fixed context length. We demonstrate the effectiveness of our approach on tasks of summarisation and question answering across different data sources, including academic papers, news articles, and conversation transcripts.
We propose a novel RoBERTa-based model, RoPPT, which introduces a target-oriented parse tree structure in metaphor detection. Compared to existing models, RoPPT focuses on semantically relevant information and achieves the state-of-the-art on several main metaphor datasets. We also compare our approach against several popular denoising and pruning methods, demonstrating the effectiveness of our approach in context denoising. Our code and dataset can be found at https://github.com/MajiBear000/RoPPT
In this paper, we propose FrameBERT, a RoBERTa-based model that can explicitly learn and incorporate FrameNet Embeddings for concept-level metaphor detection. FrameBERT not only achieves better or comparable performance to the state-of-the-art, but also is more explainable and interpretable compared to existing models, attributing to its ability of accounting for external knowledge of FrameNet.
Metaphors are proven to have stronger emotional impact than literal expressions. Although this conclusion is shown to be promising in benefiting various NLP applications, the reasons behind this phenomenon are not well studied. This paper conducts the first study in exploring how metaphors convey stronger emotion than their literal counterparts. We find that metaphors are generally more specific than literal expressions. The more specific property of metaphor can be one of the reasons for metaphors' superiority in emotion expression. When we compare metaphors with literal expressions with the same specificity level, the gap of emotion expressing ability between both reduces significantly. In addition, we observe specificity is crucial in literal language as well, as literal language can express stronger emotion by making it more specific.
Nominal metaphors are frequently used in human language and have been shown to be effective in persuading, expressing emotion, and stimulating interest. This paper tackles the problem of Chinese Nominal Metaphor (NM) generation. We introduce a novel multitask framework, which jointly optimizes three tasks: NM identification, NM component identification, and NM generation. The metaphor identification module is able to perform a self-training procedure, which discovers novel metaphors from a large-scale unlabeled corpus for NM generation. The NM component identification module emphasizes components during training and conditions the generation on these NM components for more coherent results. To train the NM identification and component identification modules, we construct an annotated corpus consisting of 6.3k sentences that contain diverse metaphorical patterns. Automatic metrics show that our method can produce diverse metaphors with good readability, where 92\% of them are novel metaphorical comparisons. Human evaluation shows our model significantly outperforms baselines on consistency and creativity.