ACL 2024 论文列表

Logical reasoning task has attracted great interest since it was proposed. Faced with such a task, current competitive models, even large language models (e.g., ChatGPT and PaLM 2), still perform badly. Previous promising LMs struggle in logical consistency modeling and logical structure perception. To this end, we model the logical reasoning task by transforming each logical sample into reasoning paths and propose an architecture PathReasoner. It addresses the task from the views of both data and model. To expand the diversity of the logical samples, we propose an atom extension strategy supported by equivalent logical formulas, to form new reasoning paths. From the model perspective, we design a stack of transformer-style blocks. In particular, we propose a path-attention module to joint model in-atom and cross-atom relations with the high-order diffusion strategy. Experiments show that PathReasoner achieves competitive performances on two logical reasoning benchmarks and great generalization abilities.

The design choices in Transformer feed-forward neural networks have resulted in significant computational and parameter overhead. In this work, we emphasize the importance of hidden dimensions in designing lightweight FFNs, a factor often overlooked in previous architectures. Guided by this principle, we introduce PartialFormer, a parameter-efficient Transformer architecture utilizing multiple smaller FFNs to reduce parameters and computation while maintaining essential hidden dimensions. These smaller FFNs are integrated into a multi-head attention mechanism for effective collaboration. We also propose a tailored head scaling strategy to enhance PartialFormer’s capabilities. Furthermore, we present a residual-like attention calculation to improve depth scaling within PartialFormer. Extensive experiments on 9 translation tasks and 1 abstractive summarization task validate the effectiveness of our PartialFormer approach on machine translation and summarization tasks. Our code would be available at: https://github.com/zhengkid/PartialFormer.

Modern natural language processing (NLP) systems thrive when given access to large datasets. However, a large fraction of the world’s languages are not privy to such benefits due to sparse documentation and inadequate digital representation. This is especially true for Indian regional languages. As a first step towards expanding the reach of NLP technologies to extremely low-resource Indian languages, we present a new parallel part-of-speech (POS) evaluation dataset for Angika, Magahi, Bhojpuri and Hindi. Angika, Magahi, Bhojpuri, along with the more well-known Hindi, are all languages spoken in the Indian states of Bihar, Jharkhand and West Bengal. Ours is notably the first NLP resource, even for a shallow NLP task like POS-tagging, for Angika. We establish POS-tagging baselines using state-of-the-art multilingual pretrained language models (PLMs) finetuned on Hindi data, and show zero-shot evaluations on the other three languages. While all four languages use the same Devanagari script, pretrained tokenizers underperform in zero-shot on the three languages. We propose a simple look-back fix to address the tokenization challenge yielding F1-score improvements of up to 8% on Angika and show how it comes very close to an oracle setting when the underlying Hindi word is known (and can be accurately tokenized).

Humans often interact with large language models (LLMs) in multi-turn interaction to obtain desired answers or more information. However, most existing studies overlook the multi-turn instruction following ability of LLMs, in terms of training dataset, training method, and evaluation benchmark. In this paper, we introduce Parrot, a solution aiming to enhance multi-turn instruction following for LLMs. First, we introduce an efficient but effective method for collecting multi-turn instructions that feature human-like queries, such as anaphora and ellipsis. Second, we propose a context-aware preference optimization strategy to further enhance LLMs for complex queries in multi-turn interaction. Moreover, to quantitatively evaluate LLMs in multi-turn instruction following, we manually build a multi-turn benchmark derived from existing ones. Extensive experiments show that Parrot improves current LLMs by up to 7.2% in multi-turn instruction following. Our dataset and codes will be open-sourced to facilitate future research.

Large Language Models (LLMs) have shown impressive abilities in many applications. When a concrete and precise answer is desired, it is important to have a quantitative estimation of the potential error rate. However, this can be challenging due to the text-in-text-out nature of the generative models. We present a method based on Pareto optimization that generates a risk score to estimate the probability of error in an LLM response by integrating multiple sources of information. We prove theoretically that the error estimator optimized in our framework aligns with the LLM and the information sources in an Pareto optimal manner. Experimental results show that the risk scores estimated by our method are well correlated with the true LLM error rate, thus facilitating error correction. By dynamically combining with prompting strategies such as self-verification and information retrieval, we demonstrate the proposed method can be utilized to increase the performance of an LLM, surpassing state-of-the-art task specific model.

Negation is a common linguistic phenomenon. Yet language models face challenges with negation in many natural language understanding tasks such as question answering and natural language inference. In this paper, we experiment with seamless strategies that incorporate affirmative interpretations (i.e., paraphrases without negation) to make models more robust against negation. Crucially, our affirmative interpretations are obtained automatically. We show improvements with CondaQA, a large corpus requiring reasoning with negation, and five natural language understanding tasks.

Pre-trained language models (LMs) are capable of in-context learning (ICL): they can adapt to a task with only a few examples given in the prompt without any parameter update. However, it is unclear where this capability comes from as there is a stark distribution shift between pre-training text and ICL prompts. In this work, we study what patterns of the pre-training data contribute to ICL. We find that LMs’ ICL ability depends on parallel structures in the pre-training data—pairs of phrases following similar templates in the same context window. Specifically, we detect parallel structures by checking whether training on one phrase improves prediction of the other, and conduct ablation experiments to study their effect on ICL. We show that removing parallel structures in the pre-training data reduces LMs’ ICL accuracy by 51% (vs 2% from random ablation). This drop persists even when excluding common patterns such as n-gram repetitions and long-range dependency, showing the diversity and generality of parallel structures. A closer look at the detected parallel structures indicates that they cover diverse linguistic tasks and span long distances in the data.

Counterfactually Augmented Data (CAD) involves creating new data samples by applying minimal yet sufficient modifications to flip the label of existing data samples to other classes. Training with CAD enhances model robustness against spurious features that happen to correlate with labels by spreading the casual relationships across different classes. Yet, recent research reveals that training with CAD may lead models to overly focus on modified features while ignoring other important contextual information, inadvertently introducing biases that may impair performance on out-of-distribution (OOD) datasets. To mitigate this issue, we employ contrastive learning to promote global feature alignment in addition to learning counterfactual clues. We theoretically prove that contrastive loss can encourage models to leverage a broader range of features beyond those modified ones. Comprehensive experiments on two human-edited CAD datasets demonstrate that our proposed method outperforms the state-of-the-art on OOD datasets.

LLMs have demonstrated remarkable capability for understanding semantics, but their understanding of pragmatics is not well studied. To this end, we release a Pragmatics Understanding Benchmark (PUB) dataset consisting of fourteen tasks in four pragmatics phenomena, namely; Implicature, Presupposition, Reference, and Deixis. We curate high-quality test sets for each task, consisting of Multiple Choice Question Answers (MCQA). PUB includes a total of 28k data points, 6.1k are newly annotated. We evaluate nine models varying in the number of parameters and type of training. Our study reveals several key observations about the pragmatic capabilities of LLMs: 1. chat-fine-tuning strongly benefits smaller models, 2. large base models are competitive with their chat-fine-tuned counterparts, 3. there is a huge variance in performance across different pragmatics phenomena, and 4. a noticeable performance gap between human capabilities and model capabilities. We hope that PUB will enable comprehensive evaluation of LLM’s pragmatic reasoning capabilities.

With the rapid scaling of large language models (LLMs), serving numerouslow-rank adaptations (LoRAs) concurrently has become increasingly impractical,leading to unaffordable costs and necessitating more parameter-efficientfinetuning methods. In this work, we introduce Partially Rotation-enhanced Low-Rank Adaptation (PRoLoRA), an intra-layer sharing mechanism comprising fouressential components: broadcast reduction, rotation enhancement,partially-sharing refinement, and rectified initialization strategy. As asuperset of LoRA, PRoLoRA retains its advantages, and effectively circumventthe drawbacks of peer parameter-sharing methods with superior model capacity,practical feasibility, and broad applicability. Empirical experimentsdemonstrate the remarkably higher parameter efficiency of PRoLoRA in bothspecific parameter budget and performance target scenarios, and its scalabilityto larger LLMs. Notably, with one time less trainable parameters, PRoLoRA stilloutperforms LoRA on multiple instruction tuning datasets. Subsequently, anablation study is conducted to validate the necessity of individual componentsand highlight the superiority of PRoLoRA over three potential variants.Hopefully, the conspicuously higher parameter efficiency can establish PRoLoRAas a resource-friendly alternative to LoRA.

Prompt engineering is critical for the development of LLM-based applications. However, it is usually done manually in a “trial and error” fashion that can be time consuming, ineffective, and sub-optimal. Even for the prompts which seemingly work well, there is always a lingering question: can the prompts be made better with further modifications?To address these problems, we investigate automated prompt engineering in this paper. Specifically, we propose PRewrite, an automated method to rewrite an under-optimized prompt to a more effective prompt. We instantiate the prompt rewriter using an LLM. The rewriter LLM is trained using reinforcement learning to optimize the performance on a given downstream task. We conduct experiments on diverse benchmark datasets, which demonstrates the effectiveness of PRewrite.

Large language models (LLMs) are typically aligned to be harmless to humans. Unfortunately, recent work has shown that such models are susceptible to automated jailbreak attacks that induce them to generate harmful content. More recent LLMs often incorporate an additional layer of defense, a Guard Model, which is a second LLM that is designed to check and moderate the output response of the primary LLM. Our key contribution is to show a novel attack strategy, PRP, that is successful against several open-source (e.g., Llama 2) and closed-source (e.g., GPT 3.5) implementations of Guard Models. PRP leverages a two step prefix-based attack that operates by (a) constructing a universal adversarial prefix for the Guard Model, and (b) propagating this prefix to the response. We find that this procedure is effective across multiple threat models, including ones in which the adversary has no access to the Guard Model at all. Our work suggests that further advances are required on defenses and Guard Models before they can be considered effective. Code at https://github.com/AshishHoodaIITD/prp-llm-guard-rail-attack.

Pairwise Ranking Prompting (PRP) demonstrates impressive effectiveness in zero-shot document re-ranking tasks with large language models (LLMs). However, in the existing methods, PRP only outputs the same label for the comparison results of different confidence intervals without considering the uncertainty of pairwise comparison, which implies an underutilization of the generation probability information of LLMs. To bridge this gap, we propose PRP-Graph, a novel pairwise re-ranking approach, based on a refined scoring PRP unit that exploits the output probabilities of target labels to capture the degree of certainty of the comparison results. Specifically, the PRP-Graph consists of two stages, namely ranking graph construction and ranking graph aggregation. Extensive experiments conducted on the BEIR benchmark demonstrate the superiority of our approach over existing PRP-based methods. Comprehensive analysis reveals that the PRP-Graph displays strong robustness towards the initial ranking order and delivers exceptional re-ranking results with acceptable efficiency. Our code and data are available at https://github.com/Memelank/PRP-Graph.

Visually-rich document information extraction (VIE) is a vital aspect of document understanding, wherein Semantic Entity Recognition (SER) plays a significant role. However, few-shot SER on visually-rich documents remains relatively unexplored despite its considerable potential for practical applications. To address this issue, we propose a simple yet effective Plug-and-Play Tag-guided method for few-shot Semantic Entity Recognition (PPTSER) on visually-rich documents. PPTSER is built upon off-the-shelf multi-modal pre-trained models. It leverages the semantics of the tags to guide the SER task, reformulating SER into entity typing and span detection, handling both tasks simultaneously via cross-attention. Experimental results illustrate that PPTSER outperforms existing fine-tuning and few-shot methods, especially in low-data regimes. With full training data, PPTSER achieves comparable or superior performance to fine-tuning baseline. For instance, on the FUNSD benchmark, our method improves the performance of LayoutLMv3-base in 1-shot, 3-shot and 5-shot scenarios by 15.61%, 2.13%, and 2.01%, respectively. Overall, PPTSER demonstrates promising generalizability, effectiveness, and plug-and-play nature for few-shot SER on visually-rich documents. The codes will be available at [https://github.com/whlscut/PPTSER](https://github.com/whlscut/PPTSER).

Recent evaluations of Large Language Models (LLMs) have centered around testing their zero-shot/few-shot capabilities for basic natural language tasks and their ability to translate instructions into tool APIs. However, the evaluation of LLMs utilizing complex tools to finish multi-turn, multi-modal instructions in a complex multi-modal environment has not been investigated. To address this gap, we introduce the PowerPoint Task Completion (PPTC) benchmark to assess LLMs’ ability to create and edit PPT files based on user instructions. It contains 279 multi-turn sessions covering diverse topics and hundreds of instructions involving multi-modal operations. We also propose the PPTX-Match Evaluation System that evaluates if LLMs finish the instruction based on the prediction file rather than the label API sequence, thus it supports various LLM-generated API sequences. We measure 3 closed LLMs and 6 open-source LLMs. The results show that GPT-4 outperforms other LLMs with 75.1% accuracy in single-turn dialogue testing but faces challenges in completing entire sessions, achieving just 6% session accuracy. We find three main error causes in our benchmark: error accumulation in the multi-turn session, long PPT template processing, and multi-modality perception. These pose great challenges for future LLM and agent systems .

The objective of the Causal Emotion Entailment (CEE) task is to identify the causes of the target emotional utterances in a given conversation. Most existing studies have focused on a fine-tuning paradigm based on a pretrained model, e.g., the BERT model. However, there are gaps between the pretrained task and the CEE task. Although a pretrained model enhances contextual comprehension to some extent, it cannot acquire specific knowledge that is relevant to the CEE task. In addition, in a typical CEE task, there are peculiarities in the distribution of the positions with different emotion types of emotion utterances and cause utterances in conversations. Existing methods employ a fixed-size window to capture the relationship between neighboring conversations; however, these methods ignore the specific semantic associations between emotions and cause utterances. To address these issues, we propose the Position-oriented Prompt-tuning (POP-CEE) model to solve the CEE task in an end-to-end manner. Specifically, we can model the CEE task by designing prompts with multiple unified goals and by exploring the positional relationship between emotion and cause utterances using a position constraint module. Experimental results demonstrate that the proposed POP-CEE model achieves state-of-the-art performance on a benchmark dataset. Ourcode and data can be found at: https://github.com/Zh0uzh/POP-CEE.

Low-resource languages (LRLs) face challenges in supervised neural machine translation (NMT) due to limited parallel data, prompting research in unsupervised NMT.Unsupervised NMT (UNMT), without requiring ground truth, provides solutions for LRL translations using synthetic pseudo-parallel data and parallel data from auxiliary language pairs. However, they usually encounter translation errors, including errors from synthetic data and from auxiliary language pairs with linguistic biases.We argue that large language models (LLMs) mitigate UNMT’s translation errors by dynamically organizing auxiliary languages in prompts to improve LRL translations. In this paper, we propose PrObability-driven Meta-graph Prompter (POMP), an approach employing a dynamic graph to organize multiple auxiliary languages, to prompt LLMs in LRL translations. POMP proposes a language-specific meta-graph that dynamically samples multiple translation paths to organize auxiliary languages in constructing prompts. Following the path, POMP prompts LLMs to translate with a mixture of auxiliary languages. We achieve the meta-graph’s evolution by back-propagating evaluation scores to update probabilities on the graph.Our experimental improvements show POMP’s effectiveness on LRLs’ translation.

Large Language Models (LLMs) have exhibited impressive capabilities in various tasks, yet their vast parameter sizes restrict their applicability in resource-constrained settings. Knowledge distillation (KD) offers a viable solution by transferring expertise from large teacher models to compact student models. However, traditional KD techniques face specific challenges when applied to LLMs, including restricted access to LLM outputs, significant teacher-student capacity gaps, and the inherited mis-calibration issue. In this work, we present PLaD, a novel preference-based LLM distillation framework. PLaD exploits the teacher-student capacity discrepancy to generate pseudo-preference pairs where teacher outputs are preferred over student outputs. Then, PLaD leverages a ranking loss to re-calibrate the student’s estimation of sequence likelihood, which steers the student’s focus towards understanding the relative quality of outputs instead of simply imitating the teacher. PLaD bypasses the need for access to teacher LLM’s internal states, tackles the student’s expressivity limitations, and mitigates the student mis-calibration issue. Through extensive experiments on two sequence generation tasks and with various LLMs, we demonstrate the effectiveness of our proposed PLaD framework.

Instruction tuning has remarkably advanced large language models (LLMs) in understanding and responding to diverse human instructions. Despite the success in high-resource languages, its application in lower-resource ones faces challenges due to the imbalanced foundational abilities of LLMs across different languages, stemming from the uneven language distribution in their pre-training data. To tackle this issue, we propose pivot language guided generation (PLUG), an approach that utilizes a high-resource language, primarily English, as the pivot to enhance instruction tuning in lower-resource languages. It trains the model to first process instructions in the pivot language, and then produce responses in the target language. To evaluate our approach, we introduce a benchmark, X-AlpacaEval, of instructions in 4 languages (Chinese, Korean, Italian, and Spanish), each annotated by professional translators. Our approach demonstrates a significant improvement in the instruction-following abilities of LLMs by 29% on average, compared to directly responding in the target language alone. Further experiments validate the versatility of our approach by employing alternative pivot languages beyond English to assist languages where LLMs exhibit lower proficiency. Code and data are available at https://github.com/ytyz1307zzh/PLUG.