Jian Liu

Hanmeng Liu, Ruoxi Ning, Zhiyang Teng et al. · bytedance

Harnessing logical reasoning ability is a comprehensive natural language understanding endeavor. With the release of Generative Pretrained Transformer 4 (GPT-4), highlighted as "advanced" at reasoning tasks, we are eager to learn the GPT-4 performance on various logical reasoning tasks. This report analyses multiple logical reasoning datasets, with popular benchmarks like LogiQA and ReClor, and newly-released datasets like AR-LSAT. We test the multi-choice reading comprehension and natural language inference tasks with benchmarks requiring logical reasoning. We further construct a logical reasoning out-of-distribution dataset to investigate the robustness of ChatGPT and GPT-4. We also make a performance comparison between ChatGPT and GPT-4. Experiment results show that ChatGPT performs significantly better than the RoBERTa fine-tuning method on most logical reasoning benchmarks. With early access to the GPT-4 API we are able to conduct intense experiments on the GPT-4 model. The results show GPT-4 yields even higher performance on most logical reasoning datasets. Among benchmarks, ChatGPT and GPT-4 do relatively well on well-known datasets like LogiQA and ReClor. However, the performance drops significantly when handling newly released and out-of-distribution datasets. Logical reasoning remains challenging for ChatGPT and GPT-4, especially on out-of-distribution and natural language inference datasets. We release the prompt-style logical reasoning datasets as a benchmark suite and name it LogiEval.

Songming Zhang, Yijin Liu, Fandong Meng et al. · tsinghua

Token-level adaptive training approaches can alleviate the token imbalance problem and thus improve neural machine translation, through re-weighting the losses of different target tokens based on specific statistical metrics (e.g., token frequency or mutual information). Given that standard translation models make predictions on the condition of previous target contexts, we argue that the above statistical metrics ignore target context information and may assign inappropriate weights to target tokens. While one possible solution is to directly take target contexts into these statistical metrics, the target-context-aware statistical computing is extremely expensive, and the corresponding storage overhead is unrealistic. To solve the above issues, we propose a target-context-aware metric, named conditional bilingual mutual information (CBMI), which makes it feasible to supplement target context information for statistical metrics. Particularly, our CBMI can be formalized as the log quotient of the translation model probability and language model probability by decomposing the conditional joint distribution. Thus CBMI can be efficiently calculated during model training without any pre-specific statistical calculations and large storage overhead. Furthermore, we propose an effective adaptive training approach based on both the token- and sentence-level CBMI. Experimental results on WMT14 English-German and WMT19 Chinese-English tasks show our approach can significantly outperform the Transformer baseline and other related methods.

Kangyun Ning, Yisong Su, Xueqiang Lv et al.

Although Large Language Models (LLMs) excel in NLP tasks, they still need external tools to extend their ability. Current research on tool learning with LLMs often assumes mandatory tool use, which does not always align with real-world situations, where the necessity for tools is uncertain, and incorrect or unnecessary use of tools can damage the general abilities of LLMs. Therefore, we propose to explore whether LLMs can discern their ability boundaries and use tools flexibly. We then introduce the Whether-or-not tool usage Evaluation benchmark (WTU-Eval) to assess LLMs with eleven datasets, where six of them are tool-usage datasets, and five are general datasets. LLMs are prompted to use tools according to their needs. The results of eight LLMs on WTU-Eval reveal that LLMs frequently struggle to determine tool use in general datasets, and LLMs' performance in tool-usage datasets improves when their ability is similar to ChatGPT. In both datasets, incorrect tool usage significantly impairs LLMs' performance. To mitigate this, we also develop the finetuning dataset to enhance tool decision-making. Fine-tuning Llama2-7B results in a 14\% average performance improvement and a 16.8\% decrease in incorrect tool usage. We will release the WTU-Eval benchmark.

Wang YuHang, Junkang Guo, Aolei Liu et al.

Adversarial robustness is a critical challenge in deploying deep neural networks for real-world applications. While adversarial training is a widely recognized defense strategy, most existing studies focus on balanced datasets, overlooking the prevalence of long-tailed distributions in real-world data, which significantly complicates robustness. This paper provides a comprehensive analysis of adversarial training under long-tailed distributions and identifies limitations in the current state-of-the-art method, AT-BSL, in achieving robust performance under such conditions. To address these challenges, we propose a novel training framework, TAET, which integrates an initial stabilization phase followed by a stratified equalization adversarial training phase. Additionally, prior work on long-tailed robustness has largely ignored the crucial evaluation metric of balanced accuracy. To bridge this gap, we introduce the concept of balanced robustness, a comprehensive metric tailored for assessing robustness under long-tailed distributions. Extensive experiments demonstrate that our method surpasses existing advanced defenses, achieving significant improvements in both memory and computational efficiency. This work represents a substantial advancement in addressing robustness challenges in real-world applications. Our code is available at: https://github.com/BuhuiOK/TAET-Two-Stage-Adversarial-Equalization-Training-on-Long-Tailed-Distributions.

Zijin Hong, Jian Liu

Event Extraction (EE) is an essential information extraction task that aims to extract event-related information from unstructured texts. The paradigm of this task has shifted from conventional classification-based methods to more contemporary question-answering-based (QA-based) approaches. However, in QA-based EE, the quality of the questions dramatically affects the extraction accuracy, and how to generate high-quality questions for QA-based EE remains a challenge. In this work, to tackle this challenge, we suggest four criteria to evaluate the quality of a question and propose a reinforcement learning method, RLQG, for QA-based EE that can generate generalizable, high-quality, and context-dependent questions and provides clear guidance to QA models. The extensive experiments conducted on ACE and RAMS datasets have strongly validated our approach's effectiveness, which also demonstrates its robustness in scenarios with limited training data. The corresponding code of RLQG is released for further research.

Jinhong Wang, Jintai Chen, Jian Liu et al.

Ordinal regression refers to classifying object instances into ordinal categories. Ordinal regression is crucial for applications in various areas like facial age estimation, image aesthetics assessment, and even cancer staging, due to its capability to utilize ordered information effectively. More importantly, it also enhances model interpretation by considering category order, aiding the understanding of data trends and causal relationships. Despite significant recent progress, challenges remain, and further investigation of ordinal regression techniques and applications is essential to guide future research. In this survey, we present a comprehensive examination of advances and applications of ordinal regression. By introducing a systematic taxonomy, we meticulously classify the pertinent techniques and applications into three well-defined categories based on different strategies and objectives: Continuous Space Discretization, Distribution Ordering Learning, and Ambiguous Instance Delving. This categorization enables a structured exploration of diverse insights in ordinal regression problems, providing a framework for a more comprehensive understanding and evaluation of this field and its related applications. To our best knowledge, this is the first systematic survey of ordinal regression, which lays a foundation for future research in this fundamental and generic domain.

Songming Zhang, Yunlong Liang, Shuaibo Wang et al.

Knowledge distillation (KD) is a promising technique for model compression in neural machine translation. However, where the knowledge hides in KD is still not clear, which may hinder the development of KD. In this work, we first unravel this mystery from an empirical perspective and show that the knowledge comes from the top-1 predictions of teachers, which also helps us build a potential connection between word- and sequence-level KD. Further, we point out two inherent issues in vanilla word-level KD based on this finding. Firstly, the current objective of KD spreads its focus to whole distributions to learn the knowledge, yet lacks special treatment on the most crucial top-1 information. Secondly, the knowledge is largely covered by the golden information due to the fact that most top-1 predictions of teachers overlap with ground-truth tokens, which further restricts the potential of KD. To address these issues, we propose a novel method named \textbf{T}op-1 \textbf{I}nformation \textbf{E}nhanced \textbf{K}nowledge \textbf{D}istillation (TIE-KD). Specifically, we design a hierarchical ranking loss to enforce the learning of the top-1 information from the teacher. Additionally, we develop an iterative KD procedure to infuse more additional knowledge by distilling on the data without ground-truth targets. Experiments on WMT'14 English-German, WMT'14 English-French and WMT'16 English-Romanian demonstrate that our method can respectively boost Transformer$_{base}$ students by +1.04, +0.60 and +1.11 BLEU scores and significantly outperform the vanilla word-level KD baseline. Besides, our method shows higher generalizability on different teacher-student capacity gaps than existing KD techniques.

Leyang Cui, Yu Wu, Jian Liu et al.

There is a recent interest in investigating few-shot NER, where the low-resource target domain has different label sets compared with a resource-rich source domain. Existing methods use a similarity-based metric. However, they cannot make full use of knowledge transfer in NER model parameters. To address the issue, we propose a template-based method for NER, treating NER as a language model ranking problem in a sequence-to-sequence framework, where original sentences and statement templates filled by candidate named entity span are regarded as the source sequence and the target sequence, respectively. For inference, the model is required to classify each candidate span based on the corresponding template scores. Our experiments demonstrate that the proposed method achieves 92.55% F1 score on the CoNLL03 (rich-resource task), and significantly better than fine-tuning BERT 10.88%, 15.34%, and 11.73% F1 score on the MIT Movie, the MIT Restaurant, and the ATIS (low-resource task), respectively.

Jian Liu, Lei Gao, Sujie Guo et al.

Named entity recognition (NER) of chemicals and drugs is a critical domain of information extraction in biochemical research. NER provides support for text mining in biochemical reactions, including entity relation extraction, attribute extraction, and metabolic response relationship extraction. However, the existence of complex naming characteristics in the biomedical field, such as polysemy and special characters, make the NER task very challenging. Here, we propose a hybrid deep learning approach to improve the recognition accuracy of NER. Specifically, our approach applies the Bidirectional Encoder Representations from Transformers (BERT) model to extract the underlying features of the text, learns a representation of the context of the text through Bi-directional Long Short-Term Memory (BILSTM), and incorporates the multi-head attention (MHATT) mechanism to extract chapter-level features. In this approach, the MHATT mechanism aims to improve the recognition accuracy of abbreviations to efficiently deal with the problem of inconsistency in full-text labels. Moreover, conditional random field (CRF) is used to label sequence tags because this probabilistic method does not need strict independence assumptions and can accommodate arbitrary context information. The experimental evaluation on a publicly-available dataset shows that the proposed hybrid approach achieves the best recognition performance; in particular, it substantially improves performance in recognizing abbreviations, polysemes, and low-frequency entities, compared with the state-of-the-art approaches. For instance, compared with the recognition accuracies for low-frequency entities produced by the BILSTM-CRF algorithm, those produced by the hybrid approach on two entity datasets (MULTIPLE and IDENTIFIER) have been increased by 80% and 21.69%, respectively.