Large language models (LLMs) are capable to perform complex reasoning by in-context learning (ICL) when provided with a few input-output demonstrations (demos) and more powerful when intermediate reasoning steps (chain of thoughts (CoT)) of the demos are given. Is it necessary to use multi-demo in ICL? In this paper, we study ICL using fewer demos for each test query on the tasks in (Wei et al., 2022). Surprisingly, we do not observe significant degradation when using only one randomly chosen demo. To study this phenomenon, for each test query, we categorize demos into “positive demos” leading to the correct answer, and “negative demos” resulting in wrong answers. Our analysis reveals an inherent bias in those widely studied datasets and the redundancy of demos: most demos are positive for a majority of test queries, which explains the good performance of ICL with one random demo. Moreover, ICL (with and w/o CoT) using only one positive demo significantly outperforms multi-demo ICL adopted by most previous works, indicating the weakness of LLMs in finding positive demo(s) for input queries, which is difficult to evaluate on the biased datasets. Furthermore, we observe a counterintuitive behavior of ICL using multi-demo, i.e., its accuracy degrades(improves) when given more positive(negative) demos. This implies that ICL can be easily misguided by interference among demos and their spurious correlations. Our analyses highlight several fundamental challenges that need to be addressed in LLMs training, ICL, and benchmark design.
论文检索
输入标题、作者或关键词，从 7,591 篇学术成果中精准定位
Steering Large Language Models for Machine Translation with Finetuning and In-Context Learning
PDF ↗Large language models (LLMs) are a promising avenue for machine translation (MT). However, current LLM-based MT systems are brittle: their effectiveness highly depends on the choice of few-shot examples and they often require extra post-processing due to overgeneration. Alternatives such as finetuning on translation instructions are computationally expensive and may weaken in-context learning capabilities, due to overspecialization. In this paper, we provide a closer look at this problem. We start by showing that adapter-based finetuning with LoRA matches the performance of traditional finetuning while reducing the number of training parameters by a factor of 50. This method also outperforms few-shot prompting and eliminates the need for post-processing or in-context examples. However, we show that finetuning generally degrades few-shot performance, hindering adaptation capabilities. Finally, to obtain the best of both worlds, we propose a simple approach that incorporates few-shot examples during finetuning. Experiments on 10 language pairs show that our proposed approach recovers the original few-shot capabilities while keeping the added benefits of finetuning.
Causal reasoning ability is crucial for numerous NLP applications. Despite the impressive emerging ability of ChatGPT in various NLP tasks, it is unclear how well ChatGPT performs in causal reasoning. In this paper, we conduct the first comprehensive evaluation of the ChatGPT’s causal reasoning capabilities. Experiments show that ChatGPT is not a good causal reasoner, but a good causal interpreter. Besides, ChatGPT has a serious hallucination on causal reasoning, possibly due to the reporting biases between causal and non-causal relationships in natural language, as well as ChatGPT’s upgrading processes, such as RLHF. The In-Context Learning (ICL) and Chain-of-Thought (COT) techniques can further exacerbate such causal hallucination. Additionally, the causal reasoning ability of ChatGPT is sensitive to the words used to express the causal concept in prompts, and close-ended prompts perform better than open-ended prompts. For events in sentences, ChatGPT excels at capturing explicit causality rather than implicit causality, and performs better in sentences with lower event density and smaller lexical distance between events.
Framing bias plays a significant role in exacerbating political polarization by distorting the perception of actual events. Media outlets with divergent political stances often use polarized language in their reporting of the same event. We propose a new loss function that encourages the model to minimize the polarity difference between the polarized input articles to reduce framing bias. Specifically, our loss is designed to jointly optimize the model to map polarity ends bidirectionally. Our experimental results demonstrate that incorporating the proposed polarity minimization loss leads to a substantial reduction in framing bias when compared to a BART-based multi-document summarization model. Notably, we find that the effectiveness of this approach is most pronounced when the model is trained to minimize the polarity loss associated with informational framing bias (i.e., skewed selection of information to report).
Semantic Parsing by Large Language Models for Intricate Updating Strategies of Zero-Shot Dialogue State Tracking
PDF ↗Zero-shot Dialogue State Tracking (DST) addresses the challenge of acquiring and annotating task-oriented dialogues, which can be time-consuming and costly. However, DST extends beyond simple slot-filling and requires effective updating strategies for tracking dialogue state as conversations progress. In this paper, we propose ParsingDST, a new In-Context Learning (ICL) method, to introduce additional intricate updating strategies in zero-shot DST. Our approach reformulates the DST task by leveraging powerful Large Language Models (LLMs) and translating the original dialogue text to JSON through semantic parsing as an intermediate state. We also design a novel framework that includes more modules to ensure the effectiveness of updating strategies in the text-to-JSON process. Experimental results demonstrate that our approach outperforms existing zero-shot DST methods on MultiWOZ, exhibiting significant improvements in Joint Goal Accuracy (JGA) and slot accuracy compared to existing ICL methods.
Autoregressive (AR) encoder-decoder neural networks have proved successful in many NLP problems, including Semantic Parsing – a task that translates natural language to machine-readable parse trees. However, the sequential prediction process of AR models can be slow. To accelerate AR for semantic parsing, we introduce a new technique called TreePiece that tokenizes a parse tree into subtrees and generates one subtree per decoding step. On TOPv2 benchmark, TreePiece shows 4.6 times faster decoding speed than standard AR, and comparable speed but significantly higher accuracy compared to Non-Autoregressive (NAR).
Machine reading comprehension (MRC) is an important area of conversation agents and draws a lot of attention. However, there is a notable limitation to current MRC benchmarks: The labeled answers are mostly either spans extracted from the target corpus or the choices of the given candidates, ignoring the natural aspect of high-quality responses. As a result, MRC models trained on these datasets can not generate human-like responses in real QA scenarios. To this end, we construct a new dataset called Penguin to promote the research of MRC, providing a training and test bed for natural response generation to real scenarios. Concretely, Penguin consists of 200k training data with high-quality fluent, and well-informed responses. Penguin is the first benchmark towards natural response generation in Chinese MRC on a relatively large scale. To address the challenges in Penguin, we develop two strong baselines: end-to-end and two-stage frameworks. Following that, we further design Prompt-BART: fine-tuning the pre-trained generative language models with a mixture of prefix prompts in Penguin. Extensive experiments validated the effectiveness of this design.
Boosting Inference Efficiency: Unleashing the Power of Parameter-Shared Pre-trained Language Models
PDF ↗Parameter-shared pre-trained language models (PLMs) have emerged as a successful approach in resource-constrained environments, enabling substantial reductions in model storage and memory costs without significant performance compromise. However, it is important to note that parameter sharing does not alleviate computational burdens associated with inference, thus impeding its practicality in situations characterized by limited stringent latency requirements or computational resources. Building upon neural ordinary differential equations (ODEs), we introduce a straightforward technique to enhance the inference efficiency of parameter-shared PLMs. Additionally, we propose a simple pre-training technique that leads to fully or partially shared models capable of achieving even greater inference acceleration. The experimental results demonstrate the effectiveness of our methods on both autoregressive and autoencoding PLMs, providing novel insights into more efficient utilization of parameter-shared models in resource-constrained settings.
Emotion-Cause analysis has attracted the attention of researchers in recent years. However, most existing datasets are limited in size and number of emotion categories. They often focus on extracting parts of the document that contain the emotion cause and fail to provide more abstractive, generalizable root cause. To bridge this gap, we introduce a large-scale dataset of emotion causes, derived from 9.8 million cleaned tweets over 15 years. We describe our curation process, which includes a comprehensive pipeline for data gathering, cleaning, labeling, and validation, ensuring the dataset’s reliability and richness. We extract emotion labels and provide abstractive summarization of the events causing emotions. The final dataset comprises over 700,000 tweets with corresponding emotion-cause pairs spanning 48 emotion classes, validated by human evaluators. The novelty of our dataset stems from its broad spectrum of emotion classes and the abstractive emotion cause that facilitates the development of an emotion-cause knowledge graph for nuanced reasoning. Our dataset will enable the design of emotion-aware systems that account for the diverse emotional responses of different people for the same event.
Grounded and well-rounded: a methodological approach to the study of cross-modal and cross-lingual grounding
PDF ↗Grounding has been argued to be a crucial component towards the development of more complete and truly semantically competent artificial intelligence systems. Literature has divided into two camps: While some argue that grounding allows for qualitatively different generalizations, others believe it can be compensated by mono-modal data quantity. Limited empirical evidence has emerged for or against either position, which we argue is due to the methodological challenges that come with studying grounding and its effects on NLP systems. In this paper, we establish a methodological framework for studying what the effects are—if any—of providing models with richer input sources than text-only. The crux of it lies in the construction of comparable samples of populations of models trained on different input modalities, so that we can tease apart the qualitative effects of different input sources from quantifiable model performances. Experiments using this framework reveal qualitative differences in model behavior between cross-modally grounded, cross-lingually grounded, and ungrounded models, which we measure both at a global dataset level as well as for specific word representations, depending on how concrete their semantics is.
Query-Focused Summarization (QFS) aims to generate summaries from source documents that can answer specific queries. Although the QFS task has gained increasing attention recently, its development is constrained by the fact that mainstream QFS models are BART variants, which are autoregressive and suffer from long-term dependencies and exposure bias. To address these problems, we adopt a diffusion language model that performs well in non-autoregressive scenarios to effectively resolve issues related to autoregressive methods. However, QFS requires guidance from queries to generate adequate summaries, while diffusion language models have limited sensitivity to queries. In this paper, we propose QFS-DLM, a non-autoregressive diffusion language model that incorporates query-document fragment relevance and query-document global relevance to enhance the adaptability of QFS tasks. Firstly, we extract key fragments from documents based on queries and assign higher weights to them, thereby emphasizing crucial and continuous information within the document. Secondly, we calculate global relevance scores between queries and documents, and then integrate these scores into the model’s loss function, enabling the model to prefer high-quality data and distance itself from low-quality data. Overall, our method achieves state-of-the-art performance on Debatepedia and PubMedQA datasets in ROUGE scores, GPT-4, and human evaluations.
Tabular mathematical reasoning task requires models to perform multi-step operations including information look-up and numerical calculation, based on heterogeneous data from tables and questions. Existing solutions tend to extend chain-of-thought (CoT) reasoning into powerful large language models (LLMs) to promote multi-hop mathematical reasoning. However, such LLM-based approaches are not a viable solution in the scenario of privatization deployment or limited resources. To address this problem, we revisit small-scale tabular language models (TaLMs) and extend chain-of-thought reasoning into TaLMs for the first time. Specifically, we propose a novel framework, TaCo, which coordinates two TaLMs responsible for CoT generation and answer inference, respectively. Besides, our framework can be combined with an external calculator to enhance accurate numerical calculation. On the TABMWP dataset, TaCo outperforms the state-of-the-art ChatGPT by 9.55% (82.60%\rightarrow92.15% in accuracy) with much less parameters (0.8B). The code will be released along with the paper.
Toward Human Readable Prompt Tuning: Kubrick’s The Shining is a good movie, and a good prompt too?
PDF ↗Large language models can perform downstream tasks in a zero-shot fashion, given natural language prompts that specify the desired behavior. Such prompts are typically hand engineered, but can also be learned with gradient-based methods from labeled data. However, it is underexplored what factors make the prompts effective, especially when the prompts are in natural language. In this paper, we investigate common attributes shared by effective prompts in classification problems. We first propose a human readable prompt tuning method (FluentPrompt) based on Langevin dynamics that incorporates a fluency constraint to find a distribution of effective and fluent prompts. Our analysis reveals that effective prompts are topically related to the task domain and calibrate the prior probability of output labels. Based on these findings, we also propose a method for generating prompts using only unlabeled data, outperforming strong baselines by an average of 7.0% accuracy across three tasks.
Incorporating Syntactic Knowledge into Pre-trained Language Model using Optimization for Overcoming Catastrophic Forgetting
PDF ↗Syntactic knowledge is invaluable information for many tasks which handle complex or long sentences, but typical pre-trained language models do not contain sufficient syntactic knowledge. Thus it results in failures in downstream tasks that require syntactic knowledge. In this paper, we explore additional training to incorporate syntactic knowledge to a language model. We designed four pre-training tasks that learn different syntactic perspectives. For adding new syntactic knowledge and keeping a good balance between the original and additional knowledge, we addressed the problem of catastrophic forgetting that prevents the model from keeping semantic information when the model learns additional syntactic knowledge. We demonstrated that additional syntactic training produced consistent performance gains while clearly avoiding catastrophic forgetting.
ConPrompt: Pre-training a Language Model with Machine-Generated Data for Implicit Hate Speech Detection
PDF ↗Implicit hate speech detection is a challenging task in text classification since no explicit cues (e.g., swear words) exist in the text. While some pre-trained language models have been developed for hate speech detection, they are not specialized in implicit hate speech. Recently, an implicit hate speech dataset with a massive number of samples has been proposed by controlling machine generation. We propose a pre-training approach, ConPrompt, to fully leverage such machine-generated data. Specifically, given a machine-generated statement, we use example statements of its origin prompt as positive samples for contrastive learning. Through pre-training with ConPrompt, we present ToxiGen-ConPrompt, a pre-trained language model for implicit hate speech detection. We conduct extensive experiments on several implicit hate speech datasets and show the superior generalization ability of ToxiGen-ConPrompt compared to other pre-trained models. Additionally, we empirically show that ConPrompt is effective in mitigating identity term bias, demonstrating that it not only makes a model more generalizable but also reduces unintended bias. We analyze the representation quality of ToxiGen-ConPrompt and show its ability to consider target group and toxicity, which are desirable features in terms of implicit hate speeches.
Hate speech causes widespread and deep-seated societal issues. Proper enforcement of hate speech laws is key for protecting groups of people against harmful and discriminatory language. However, determining what constitutes hate speech is a complex task that is highly open to subjective interpretations. Existing works do not align their systems with enforceable definitions of hate speech, which can make their outputs inconsistent with the goals of regulators. This research introduces a new perspective and task for enforceable hate speech detection centred around legal definitions, and a dataset annotated on violations of eleven possible definitions by legal experts. Given the challenge of identifying clear, legally enforceable instances of hate speech, we augment the dataset with expert-generated samples and an automatically mined challenge set. We experiment with grounding the model decision in these definitions using zero-shot and few-shot prompting. We then report results on several large language models (LLMs). With this task definition, automatic hate speech detection can be more closely aligned to enforceable laws, and hence assist in more rigorous enforcement of legal protections against harmful speech in public forums.
The performance of sentence encoders can be significantly improved through the simple practice of fine-tuning using contrastive loss. A natural question arises: what characteristics do models acquire during contrastive learning? This paper theoretically and experimentally shows that contrastive-based sentence encoders implicitly weight words based on information-theoretic quantities; that is, more informative words receive greater weight, while others receive less. The theory states that, in the lower bound of the optimal value of the contrastive learning objective, the norm of word embedding reflects the information gain associated with the distribution of surrounding words. We also conduct comprehensive experiments using various models, multiple datasets, two methods to measure the implicit weighting of models (Integrated Gradients and SHAP), and two information-theoretic quantities (information gain and self-information). The results provide empirical evidence that contrastive fine-tuning emphasizes informative words.
A key feature of modern large language models (LLMs) is their ability to perform in-context learning, a prompting technique where query- answer demonstrations are shown before the final query. This allows for generalization to novel distributions at inference time where the LLM can learn new rules without parameter updates. However, the choice of demonstrations and their relationship to a particular query can have a profound impact on model accuracy, raising concerns about the true in-context generalization capabilities (Zhao et al., 2021). In this work, we explore the robustness of the in-context learning paradigm by focusing on entities. In particular, we seek to understand the robustness of LLM in-context learning with respect to named entity replacements. We discover a significant variance in downstream performance based on the choice of the named entities, across three popular reasoning tasks and two popular LLMs. Specifically, model accuracy on the test sets can fluctuate between -2.7 to +8.0 points depending on the choice of named entity replacements. Our analysis exposes the sensitivity of LLM in-context learning with respect to named entities, and offers a simple recipe to improve test performance by hyper-parameter tuning the named entities for a given dataset. Code and datasets for reproducing the results are publicly available.
Aspect-based sentiment analysis (ABSA) aims to align aspects and corresponding sentiment expressions, so as to identify the sentiment polarities of specific aspects. Most existing ABSA methods focus on mining syntactic or semantic information, which still suffers from noisy interference introduced by the attention mechanism and dependency tree when multiple aspects exist in a sentence. To address these issues, in this paper, we revisit ABSA from a novel perspective by proposing a novel scope-assisted multi-view graph contrastive learning framework. It not only mitigates noisy interference for better locating aspect and its corresponding sentiment opinion with aspect-specific scope, but also captures the correlation and difference between sentiment polarities and syntactic/semantic information. Extensive experiments on five benchmark datasets show that our proposed approach substantially outperforms state-of-the-art methods and verifies the effectiveness and robustness of our model.
Several recent studies have shown that advanced models for natural language understanding (NLU) are prone to capture biased features that are independent of the task but spuriously correlated to labels. Such models often perform well on in-distribution (ID) datasets but fail to generalize to out-of-distribution (OOD) datasets. Existing solutions can be separated into two orthogonal approaches: model-centric methods and data-centric methods. Model-centric methods improve OOD performance at the expense of ID performance. Data-centric strategies usually boost both of them via data-level manipulations such as generative data augmentation. However, the high cost of fine-tuning a generator to produce valid samples limits the potential of such approaches. To address this issue, we propose PDD, a framework that conducts training-free Perturbations on samples containing biased features to Debias NLU Datasets. PDD works by iteratively conducting perturbations via pre-trained mask language models (MLM). PDD exhibits the advantage of low cost by adopting a training-free perturbation strategy and further improves the label consistency by utilizing label information during perturbations. Extensive experiments demonstrate that PDD shows competitive performance with previous state-of-the-art debiasing strategies. When combined with the model-centric debiasing methods, PDD establishes a new state-of-the-art.