论文检索

Anil Ramakrishna, Rahul Gupta, Jens Lehmann, Morteza Ziyadi

Recent advancements in Large language models (LLMs) have enabled them to hold free form conversations over multiple turns, but they exhibit a tendency to make unfounded and incorrect statements, commonly known as hallucinations. In particular, LLMs hallucinate frequently when given invalid questions, i.e. ones with incorrect assumptions. The most common approach to evaluate LLMs on hallucinations is to test them on Question Answering (QA) test sets such as TruthfulQA. However, LLMs are increasingly pretrained on massive text corpora scraped from the Internet, which may inevitably expose these test sets to the model during training, leading eventually to an overestimation of model performances on these test sets. In this work, we present an alternative framework to address this risk and to foster further research towards making LLMs robust against invalid questions. We name our framework INVITE: a testbed of automatically generated INValId questions to evaluaTE large language models for hallucinations. In each instantiation, our framework is set up to create a fresh batch of invalid questions by distorting valid facts in which subjects or objects are replaced by similar entities. We evaluate several state of the art LLMs against a testset generated by our framework and highlight its capacity to trigger hallucinations in these models.

Nils Feldhus, Qianli Wang, Tatiana Anikina, Sahil Chopra, Cennet Oguz, Sebastian Möller

While recently developed NLP explainability methods let us open the black box in various ways (Madsen et al., 2022), a missing ingredient in this endeavor is an interactive tool offering a conversational interface. Such a dialogue system can help users explore datasets and models with explanations in a contextualized manner, e.g. via clarification or follow-up questions, and through a natural language interface. We adapt the conversational explanation framework TalkToModel (Slack et al., 2022) to the NLP domain, add new NLP-specific operations such as free-text rationalization, and illustrate its generalizability on three NLP tasks (dialogue act classification, question answering, hate speech detection). To recognize user queries for explanations, we evaluate fine-tuned and few-shot prompting models and implement a novel adapter-based approach. We then conduct two user studies on (1) the perceived correctness and helpfulness of the dialogues, and (2) the simulatability, i.e. how objectively helpful dialogical explanations are for humans in figuring out the model’s predicted label when it’s not shown. We found rationalization and feature attribution were helpful in explaining the model behavior. Moreover, users could more reliably predict the model outcome based on an explanation dialogue rather than one-off explanations.

Shenglong Yu, Ying Zhang, Wenya Guo, Zhengkun Zhang, Ru Zhou, Xiaojie Yuan

Concept Learning requires learning the definition of a general category from given training examples. Most of the existing methods focus on learning concepts from images. However, the visual information cannot present abstract concepts exactly, which struggles the introduction of novel concepts related to known concepts (e.g., ‘Plant’\rightarrow‘Asteroids’). In this paper, inspired by the fact that humans learn most concepts through linguistic description, we introduce Linguistic Concept Learning benchmark (Licon), where concepts in diverse forms (e.g., plain attributes, images, and text) are defined by linguistic descriptions. The difficulty to learn novel concepts can be controlled by the number of attributes or the hierarchical relationships between concepts. The diverse and controllable concepts are used to support challenging evaluation tasks, including concept classification, attribute prediction, and concept relationship recognition. In addition, we design an entailment-based concept learning method (EnC) to model the relationship among concepts. Extensive experiments demonstrate the effectiveness of EnC. The benchmark will be released to the public soon.

Jun Bai, Xiaofeng Zhang, Chen Li, Hanhua Hong, Xi Xu, Chenghua Lin, Wenge Rong

Transferability estimation has been attached to great attention in the computer vision fields. Researchers try to estimate with low computational cost the performance of a model when transferred from a source task to a given target task. Considering the effectiveness of such estimations, the communities of natural language processing also began to study similar problems for the selection of pre-trained language models. However, there is a lack of a comprehensive comparison between these estimation methods yet. Also, the differences between vision and language scenarios make it doubtful whether previous conclusions can be established across fields. In this paper, we first conduct a thorough survey of existing transferability estimation methods being able to find the most suitable model, then we conduct a detailed empirical study for the surveyed methods based on the GLUE benchmark. From qualitative and quantitative analyses, we demonstrate the strengths and weaknesses of existing methods and show that H-Score generally performs well with superiorities in effectiveness and efficiency. We also outline the difficulties of consideration of training details, applicability to text generation, and consistency to certain metrics which shed light on future directions.

Zixian Guo, Yuxiang Wei, Ming Liu, Zhilong Ji, Jinfeng Bai, Yiwen Guo, Wangmeng Zuo

Parameter-efficient fine-tuning (PEFT) methods have provided an effective way for adapting large vision-language models to specific tasks or scenarios. Typically, they learn a very small scale of parameters for pre-trained models in a white-box formulation, which assumes model architectures to be known and parameters to be accessible. However, large models are often not open-source due to considerations of preventing abuse or commercial factors, hence posing a barrier to the deployment of white-box PEFT methods. To alleviate the dependence on model accessibility, we introduce collaborative black-box tuning (CBBT) for both textual prompt optimization and output feature adaptation for black-box models. Specifically, considering that the backpropagation gradients are blocked, we approximate the gradients of textual prompts by analyzing the predictions with perturbed prompts. Secondly, a lightweight adapter is deployed over the output feature of the inaccessible model, further facilitating the model adaptation process. Empowered with these designs, our CBBT is extensively evaluated on eleven downstream benchmarks and achieves remarkable improvements compared to existing black-box VL adaptation methods. Our code will be made publicly available.

Ben Wu, Yue Li, Yida Mu, Carolina Scarton, Kalina Bontcheva, Xingyi Song

In this paper, we address the limitations of the common data annotation and training methods for objective single-label classification tasks. Typically, when annotating such tasks annotators are only asked to provide a single label for each sample and annotator disagreement is discarded when a final hard label is decided through majority voting. We challenge this traditional approach, acknowledging that determining the appropriate label can be difficult due to the ambiguity and lack of context in the data samples. Rather than discarding the information from such ambiguous annotations, our soft label method makes use of them for training. Our findings indicate that additional annotator information, such as confidence, secondary label and disagreement, can be used to effectively generate soft labels. Training classifiers with these soft labels then leads to improved performance and calibration on the hard label test set.

Jiaying Lu, Yongchen Qian, Shifan Zhao, Yuanzhe Xi, Carl Yang

Previous research has demonstrated the advantages of integrating data from multiple sources over traditional unimodal data, leading to the emergence of numerous novel multimodal applications. We propose a multimodal classification benchmark MuG with eight datasets that allows researchers to evaluate and improve their models. These datasets are collected from four various genres of games that cover tabular, textual, and visual modalities. We conduct multi-aspect data analysis to provide insights into the benchmark, including label balance ratios, percentages of missing features, distributions of data within each modality, and the correlations between labels and input modalities. We further present experimental results obtained by several state-of-the-art unimodal classifiers and multimodal classifiers, which demonstrate the challenging and multimodal-dependent properties of the benchmark. MuG is released at https://github.com/lujiaying/MUG-Bench with the data, tutorials, and implemented baselines.

Zhuohan Xie, Miao Li, Trevor Cohn, Jey Lau

Numerous evaluation metrics have been developed for natural language generation tasks, but their effectiveness in evaluating stories is limited as they are not specifically tailored to assess intricate aspects of storytelling, such as fluency and interestingness. In this paper, we introduce DeltaScore, a novel methodology that uses perturbation techniques for the evaluation of nuanced story aspects. We posit that the extent to which a story excels in a specific aspect (e.g., fluency) correlates with the magnitude of its susceptibility to particular perturbations (e.g., the introduction of typos). Given this, we measure the quality of an aspect by calculating the likelihood difference between pre- and post-perturbation states using pre-trained language models. We compare DeltaScore with existing metrics on storytelling datasets from two domains in five fine-grained story aspects: fluency, coherence, relatedness, logicality, and interestingness. DeltaScore demonstrates strong performance, revealing a surprising finding that one specific perturbation proves highly effective in capturing multiple aspects. Source code is available on our GitHub repository.

Alla Chepurova, Aydar Bulatov, Yuri Kuratov, Mikhail Burtsev

Real-world Knowledge Graphs (KGs) often suffer from incompleteness, which limits their potential performance. Knowledge Graph Completion (KGC) techniques aim to address this issue. However, traditional KGC methods are computationally intensive and impractical for large-scale KGs, necessitating the learning of dense node embeddings and computing pairwise distances. Generative transformer-based language models (e.g., T5 and recent KGT5) offer a promising solution as they can predict the tail nodes directly. In this study, we propose to include node neighborhoods as additional information to improve KGC methods based on language models. We examine the effects of this imputation and show that, on both inductive and transductive Wikidata subsets, our method outperforms KGT5 and conventional KGC approaches. We also provide an extensive analysis of the impact of neighborhood on model prediction and show its importance. Furthermore, we point the way to significantly improve KGC through more effective neighborhood selection.

Yi Dai, Hao Lang, Kaisheng Zeng, Fei Huang, Yongbin Li

Out-of-distribution (OOD) detection is essential for reliable and trustworthy machine learning. Recent multi-modal OOD detection leverages textual information from in-distribution (ID) class names for visual OOD detection, yet it currently neglects the rich contextual information of ID classes. Large language models (LLMs) encode a wealth of world knowledge and can be prompted to generate descriptive features for each class. Indiscriminately using such knowledge causes catastrophic damage to OOD detection due to LLMs’ hallucinations, as is observed by our analysis. In this paper, we propose to apply world knowledge to enhance OOD detection performance through selective generation from LLMs. Specifically, we introduce a consistency-based uncertainty calibration method to estimate the confidence score of each generation. We further extract visual objects from each image to fully capitalize on the aforementioned world knowledge. Extensive experiments demonstrate that our method consistently outperforms the state-of-the-art.

Vipul Raheja, Dhruv Kumar, Ryan Koo, Dongyeop Kang

We introduce CoEdIT, a state-of-the-art text editing system for writing assistance. CoEdIT takes instructions from the user specifying the attributes of the desired text, such as “Make the sentence simpler” or “Write it in a more neutral style,” and outputs the edited text. We present a large language model fine-tuned on a diverse collection of task-specific instructions for text editing (a total of 82K instructions). Our model (1) achieves state-of-the-art performance on various text editing benchmarks, (2) is competitive with publicly available largest-sized LLMs trained on instructions while being ~60x smaller, (3) is capable of generalizing to unseen edit instructions, and (4) exhibits abilities to generalize to composite instructions containing different combinations of edit actions. Through extensive qualitative and quantitative analysis, we show that writers prefer the edits suggested by CoEdIT relative to other state-of-the-art text editing models. Our code, data, and models are publicly available at https://github.com/vipulraheja/coedit.

Satya Sai Srinath Namburi, Makesh Sreedhar, Srinath Srinivasan, Frederic Sala

Compressing large language models (LLMs), often consisting of billions of parameters, provides faster inference, smaller memory footprints, and enables local deployment. The standard compression techniques are pruning and quantization, with the former eliminating redundant connections in model layers and the latter representing model parameters with as little as 4 bits. The key tradeoff is between the degree of compression and the impact on the quality of the compressed model. Existing research on LLM compression primarily focuses on performance in terms of general metrics like perplexity or downstream task accuracy. More fine-grained metrics, such as those measuring parametric knowledge, remain significantly underexplored. To help bridge this gap, we present a comprehensive analysis across multiple model families using the LAMA and LM-Harness benchmarks in order to systematically quantify the effect of commonly employed compression techniques on model performance. A particular focus is on tradeoffs involving parametric knowledge, with the goal of providing practitioners with practical insights to make informed decisions on compression.

Tal Levy, Omer Goldman, Reut Tsarfaty

The ability to identify and control different kinds of linguistic information encoded in vector representations of words has many use cases, especially for explainability and bias removal. This is usually done via a set of simple classification tasks, termed probes, to evaluate the information encoded in the embedding space. However, the involvement of a trainable classifier leads to entanglement between the probe’s results and the classifier’s nature. As a result, contemporary works on probing include tasks that do not involve training of auxiliary models. In this work we introduce the term indicator tasks for non-trainable tasks which are used to query embedding spaces for the existence of certain properties, and claim that this kind of tasks may point to a direction opposite to probes, and that this contradiction complicates the decision on whether a property exists in an embedding space. We demonstrate our claims with two test cases, one dealing with gender debiasing and another with the erasure of morphological information from embedding spaces. We show that the application of a suitable indicator provides a more accurate picture of the information captured and removed compared to probes. We thus conclude that indicator tasks should be implemented and taken into consideration when eliciting information from embedded representations.

Zizheng Zhang, Masato Mita, Mamoru Komachi

Providing explanations for cloze questions in language assessment (LA) has been recognized as a valuable approach to enhancing the language proficiency of learners. However, there is a noticeable absence of dedicated tasks and datasets specifically designed for generating language learner explanations. In response to this gap, this paper introduces a novel task ClozEx of generating explanations for cloze questions in LA, with a particular focus on English as a Second Language (ESL) learners. To support this task, we present a meticulously curated dataset comprising cloze questions paired with corresponding explanations. This dataset aims to assess language proficiency and facilitates language learning by offering informative and accurate explanations. To tackle the task, we fine-tuned various baseline models with our training data, including encoder-decoder and decoder-only architectures. We also explored whether large language models (LLMs) are able to generate good explanations without fine-tuning, just using pre-defined prompts. The evaluation results demonstrate that encoder-decoder models have the potential to deliver fluent and valid explanations when trained on our dataset.

Shoujie Tong, Heming Xia, Damai Dai, Runxin Xu, Tianyu Liu, Binghuai Lin, Yunbo Cao, Zhifang Sui

Pretrained language models have achieved remarkable success in natural language understanding. However, fine-tuning pretrained models on limited training data tends to overfit and thus diminish performance. This paper presents Bi-Drop, a fine-tuning strategy that selectively updates model parameters using gradients from various sub-nets dynamically generated by dropout. The sub-net estimation of Bi-Drop is performed in an in-batch manner, so it overcomes the problem of hysteresis in sub-net updating, which is possessed by previous methods that perform asynchronous sub-net estimation. Also, Bi-Drop needs only one mini-batch to estimate the sub-net so it achieves higher utility of training data. Experiments on the GLUE benchmark demonstrate that Bi-Drop consistently outperforms previous fine-tuning methods. Furthermore, empirical results also show that Bi-Drop exhibits excellent generalization ability and robustness for domain transfer, data imbalance, and low-resource scenarios.

Jiefeng Chen, Jinsung Yoon, Sayna Ebrahimi, Sercan Arik, Tomas Pfister, Somesh Jha

Large language models (LLMs) have recently shown great advances in a variety of tasks, including natural language understanding and generation. However, their use in high-stakes decision-making scenarios is still limited due to the potential for errors. *Selective prediction* is a technique that can be used to improve the reliability of the LLMs by allowing them to abstain from making predictions when they are unsure of the answer. In this work, we propose a novel framework for adaptation with self-evaluation to improve the selective prediction performance of LLMs. Our framework is based on the idea of using parameter-efficient tuning to adapt the LLM to the specific task at hand while improving its ability to perform self-evaluation. We evaluate our method on a variety of question-answering (QA) datasets and show that it outperforms state-of-the-art selective prediction methods. For example, on the CoQA benchmark, our method improves the AUACC from 91.23% to 92.63% and improves the AUROC from 74.61% to 80.25%.

Hao Wang, Qingxuan Wang, Yue Li, Changqing Wang, Chenhui Chu, Rui Wang

The use of visually-rich documents in various fields has created a demand for Document AI models that can read and comprehend documents like humans, which requires the overcoming of technical, linguistic, and cognitive barriers. Unfortunately, the lack of appropriate datasets has significantly hindered advancements in the field. To address this issue, we introduce DocTrack, a visually-rich document dataset really aligned with human eye-movement information using eye-tracking technology. This dataset can be used to investigate the challenges mentioned above. Additionally, we explore the impact of human reading order on document understanding tasks and examine what would happen if a machine reads in the same order as a human. Our results suggest that although Document AI models have made significant progresses, they still have a long way to go before they can read visually richer documents as accurately, continuously, and flexibly as humans do. These findings have potential implications for future research and development of document intelligence.

Guoxin Chen, Yiming Qian, Bowen Wang, Liangzhi Li

The large language models have achieved superior performance on various natural language tasks. One major drawback of such approaches is they are resource-intensive in fine-tuning new datasets. Soft-prompt tuning presents a resource-efficient solution to fine-tune the pre-trained language models (PLMs) while keeping their weight frozen. Existing soft prompt methods mainly focus on designing the input-independent prompts that steer the model to fit the domain of the new dataset. Those methods often ignore the fine-grained information about the task and context of the text. In this paper, we propose a multi-level prompt tuning (MPrompt) method for machine reading comprehension. It utilizes prompts at task-specific, domain-specific, and context-specific levels to enhance the comprehension of input semantics at different granularities. We also propose an independence constraint to steer each domain-specific prompt to focus on information within its domain to avoid redundancy. Moreover, we present a prompt generator that incorporates context-related knowledge in the prompt generation to enhance contextual relevancy. We conducted extensive experiments on 12 benchmarks of various QA formats and achieved an average improvement of 1.94% over the state-of-the-art methods.

Verna Dankers, Christopher Lucas

When natural language phrases are combined, their meaning is often more than the sum of their parts. In the context of NLP tasks such as sentiment analysis, where the meaning of a phrase is its sentiment, that still applies. Many NLP studies on sentiment analysis, however, focus on the fact that sentiment computations are largely compositional. We, instead, set out to obtain non-compositionality ratings for phrases with respect to their sentiment. Our contributions are as follows: a) a methodology for obtaining those non-compositionality ratings, b) a resource of ratings for 259 phrases – NonCompSST – along with an analysis of that resource, and c) an evaluation of computational models for sentiment analysis using this new resource.

Yuiko Tsunomori, Masakazu Ishihata, Hiroaki Sugiyama

In the last few years, generative dialogue models have shown excellent performance and have been used for various applications. As chatbots become more prevalent in our daily lives, more and more people expect them to behave more like humans, but existing dialogue models do not consider the time information that people are constantly aware of. In this paper, we aim to construct a time-considerable dialogue model that actively utilizes time information. First, we categorize responses by their naturalness at different times and introduce a new metric to classify responses into our categories. Then, we propose a new reranking method to make the existing dialogue model time-considerable using the proposed metric and subjectively evaluate the performances of the obtained time-considerable dialogue models by humans.