Open-domain multi-turn dialogue generation encounters the significant challenge of lacking various types of knowledge from diverse sources. Existing models typically focus on identifying specific types of dialogue knowledge and utilize corresponding datasets for training. However, this approach often leads to limited generalization capabilities and increased computational resource requirements. Recently, large language models (LLMs) have shown impressive performance on natural language processing tasks. To harness the knowledge storage of LLMs, we propose a framework named KnowEE that explores multi-source multi-type knowledge from LLMs by leveraging diverse datasets and then exploits the obtained knowledge for response generation. Our framework comprises two phases: First, we leverage five external datasets encompassing various types of knowledge to extract the most relevant samples to the dialogue context which are served as prompts to generate corresponding type of knowledge; Second, we inject the acquired knowledge into the ongoing dialogue context in fine-grained and coarse-grained manners, which is then fed into LLMs to generate the final dialogue response. Both automatic and manual evaluation results validate the effectiveness of our framework in exploring and exploiting multi-source multi-type knowledge to generate coherent, informative, and fluent responses.
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
Hallucination Mitigation in Natural Language Generation from Large-Scale Open-Domain Knowledge Graphs
PDF ↗In generating natural language descriptions for knowledge graph triples, prior works used either small-scale, human-annotated datasets or datasets with limited variety of graph shapes, e.g., those having mostly star graphs. Graph-to-text models trained and evaluated on such datasets are largely not assessed for more realistic large-scale, open-domain settings. We introduce a new dataset, GraphNarrative, to fill this gap. Fine-tuning transformer-based pre-trained language models has achieved state-of-the-art performance among graph-to-text models. However, this method suffers from information hallucination—the generated text may contain fabricated facts not present in input graphs. We propose a novel approach that, given a graph-sentence pair in GraphNarrative, trims the sentence to eliminate portions that are not present in the corresponding graph, by utilizing the sentence’s dependency parse tree. Our experiment results verify this approach using models trained on GraphNarrative and existing datasets. The dataset, source code, and trained models are released at https://github.com/idirlab/graphnarrator.
Dialogue comprehension and generation are vital to the success of open-domain dialogue systems. Although pre-trained generative conversation models have made significant progress in generating fluent responses, people have difficulty judging whether they understand and efficiently model the contextual information of the conversation. In this study, we propose a Multi-Source Probing (MSP) method to probe the dialogue comprehension abilities of open-domain dialogue models. MSP aggregates features from multiple sources to accomplish diverse task goals and conducts downstream tasks in a generative manner that is consistent with dialogue model pre-training to leverage model capabilities. We conduct probing experiments on seven tasks that require various dialogue comprehension skills, based on the internal representations encoded by dialogue models. Experimental results show that open-domain dialogue models can encode semantic information in the intermediate hidden states, which facilitates dialogue comprehension tasks. Models of different scales and structures possess different conversational understanding capabilities. Our findings encourage a comprehensive evaluation and design of open-domain dialogue models.
The recent advent of end-to-end generative retrieval marks a significant shift in document retrieval methods, leveraging differentiable search indexes to directly produce relevant document identifiers (docids) in response to a specific query. Nevertheless, this approach faces two fundamental challenges: (i) a discrepancy between the token-level probabilistic optimization and the broader document-level relevance estimation; (ii) an overemphasis on top-1 results at the expense of overall ranking quality. To tackle these challenges, we propose a generative retrieval model with reinforcement learning from relevance feedback, which aims to align token-level docid generation with document-level relevance estimation. The training process incorporates three stages: supervised fine-tuning, relevance reward model training, and reinforced learning-to-rank from relevance feedback. To train a high-quality reward model, we define “relevance” under three progressive scenarios, which collectively offer a comprehensive evaluation of the document relevance. Experiments conducted on two benchmark datasets demonstrate the effectiveness of our proposed approach.
Minimum Bayes risk (MBR) decoding outputs the hypothesis with the highest expected utility over the model distribution for some utility function. It has been shown to improve accuracy over beam search in conditional language generation problems and especially neural machine translation, in both human and automatic evaluations. However, the standard sampling-based algorithm for MBR is substantially more computationally expensive than beam search, requiring a large number of samples as well as a quadratic number of calls to the utility function, limiting its applicability. We describe an algorithm for MBR which gradually grows the number of samples used to estimate the utility while pruning hypotheses that are unlikely to have the highest utility according to confidence estimates obtained with bootstrap sampling. Our method requires fewer samples and drastically reduces the number of calls to the utility function compared to standard MBR while being statistically indistinguishable in terms of accuracy. We demonstrate the effectiveness of our approach in experiments on three language pairs, using chrF++ and COMET as utility/evaluation metrics.
Clinical trials are critical for drug development. Constructing the appropriate eligibility criteria (i.e., the inclusion/exclusion criteria for patient recruitment) is essential for the trial’s success. Proper design of clinical trial protocols should consider similar precedent trials and their eligibility criteria to ensure sufficient patient coverage. In this paper, we present a method named AutoTrial to aid the design of clinical eligibility criteria using language models. It allows (1) controllable generation under instructions via a hybrid of discrete and neural prompting, (2) scalable knowledge incorporation via in-context learning, and (3) explicit reasoning chains to provide rationales for understanding the outputs. Experiments on over 70K clinical trials verify that AutoTrial generates high-quality criteria texts that are fluent and coherent and with high accuracy in capturing the relevant clinical concepts to the target trial. It is noteworthy that our method, with a much smaller parameter size, gains around 60% winning rate against the GPT-3.5 baselines via human evaluations.
How much private information do text embeddings reveal about the original text? We investigate the problem of embedding inversion, reconstructing the full text represented in dense text embeddings. We frame the problem as controlled generation: generating text that, when reembedded, is close to a fixed point in latent space. We find that although a naive model conditioned on the embedding performs poorly, a multi-step method that iteratively corrects and re-embeds text is able to recover 92% of 32-token text inputs exactly. We train our model to decode text embeddings from two state-of-the-art embedding models, and also show that our model can recover important personal information (full names) from a dataset of clinical notes.
Machine translation (MT) quality estimation (QE) is a crucial task to estimate the quality of MT outputs when reference translations are unavailable. Many studies focus on generating pseudo data using large parallel corpus and achieve remarkable success in the supervised setting. However, pseudo data solutions are less satisfying in unsupervised scenarios because the pseudo labels are inaccurate or the pseudo translations differ from the real ones. To address these problems, we propose to generate pseudo data using the MT model with constrained beam search (CBSQE). CBSQE preserves the reference parts with high MT probabilities as correct translations, while the rest parts as the wrong ones for MT generation. Therefore, CBSQE can reduce the false negative labels caused by synonyms. Overall, beam search will prefer a more real hypothesis with a higher MT generation likelihood. Extensive experiments demonstrate that CBSQE outperforms strong baselines in both supervised and unsupervised settings. Analyses further show the superiority of CBSQE. The code is available at https://github.com/NJUNLP/njuqe.
Comparative reasoning is a process of comparing objects, concepts, or entities to draw conclusions, which constitutes a fundamental cognitive ability. In this paper, we propose a novel framework to pre-train language models for enhancing their abilities of comparative reasoning over texts. While there have been approaches for NLP tasks that require comparative reasoning, they suffer from costly manual data labeling and limited generalizability to different tasks. Our approach introduces a novel method of collecting scalable data for text-based entity comparison, which leverages both structured and unstructured data. Moreover, we present a framework of pre-training language models via three novel objectives on comparative reasoning. Evaluation on downstream tasks including comparative question answering, question generation, and summarization shows that our pre-training framework significantly improves the comparative reasoning abilities of language models, especially under low-resource conditions. This work also releases the first integrated benchmark for comparative reasoning.
For a language model (LM) to faithfully model human language, it must compress vast, potentially infinite information into relatively few dimensions. We propose analyzing compression in (pre-trained) LMs from two points of view: geometric and information-theoretic. We demonstrate that the two views are highly correlated, such that the intrinsic geometric dimension of linguistic data predicts their coding length under the LM. We then show that, in turn, high compression of a linguistic dataset predicts rapid adaptation to that dataset, confirming that being able to compress linguistic information is an important part of successful LM performance. As a practical byproduct of our analysis, we evaluate a battery of intrinsic dimension estimators for the first time on linguistic data, showing that only some encapsulate the relationship between information-theoretic compression, geometric compression, and ease-of-adaptation.
A popular approach for improving the correctness of output from large language models (LLMs) is Self-Consistency - poll the LLM multiple times and output the most frequent solution. Existing Self-Consistency techniques always generate a constant number of samples per question, where a better approach will be to non-uniformly distribute the available budget based on the amount of agreement in the samples generated so far. In response, we introduce Adaptive-Consistency, a cost-efficient, model-agnostic technique that dynamically adjusts the number of samples per question using a lightweight stopping criterion. Our experiments over 17 reasoning and code generation datasets and three LLMs demonstrate that Adaptive-Consistency reduces sample budget by up to 7.9 times with an average accuracy drop of less than 0.1%
Large Language Models Only Pass Primary School Exams in Indonesia: A Comprehensive Test on IndoMMLU
PDF ↗Although large language models (LLMs) are often pre-trained on large-scale multilingual texts, their reasoning abilities and real-world knowledge are mainly evaluated based on English datasets. Assessing LLM capabilities beyond English is increasingly vital but hindered due to the lack of suitable datasets. In this work, we introduce IndoMMLU, the first multi-task language understanding benchmark for Indonesian culture and languages, which consists of questions from primary school to university entrance exams in Indonesia. By employing professional teachers, we obtain 14,981 questions across 64 tasks and education levels, with 46% of the questions focusing on assessing proficiency in the Indonesian language and knowledge of nine local languages and cultures in Indonesia. Our empirical evaluations show that GPT-3.5 only manages to pass the Indonesian primary school level, with limited knowledge of local Indonesian languages and culture. Other smaller models such as BLOOMZ and Falcon perform at even lower levels.
KRLS: Improving End-to-End Response Generation in Task Oriented Dialog with Reinforced Keywords Learning
PDF ↗In task-oriented dialogs (TOD), reinforcement learning (RL) algorithms train a model to directly optimize response for task-related metrics. However, RL often needs to perform exploration, which can be time-consuming due to the slow auto-regressive sequence generation process. We investigate an approach to create a more efficient RL-based algorithm to improve TOD performance in an offline setting. First, we use a faster generation procedure that samples from independent next-word distributions after training the language model (LM) with supervised learning. We then introduce a fine-grained reward function to help the model focus on learning key information in a dialog, by measuring the importance and semantic closeness of each generated token. Experiments on the MultiWoZ dataset show our new training algorithm, Keywords Reinforcement Learning with Next-word Sampling (KRLS), achieves state-of-the-art performance on the end-to-end response generation task, with a 15% training time reduction compared to a standard RL algorithm using auto-regressive generation.
Large Language Models (LLMs) are popular for their impressive abilities, but the need for model-specific fine-tuning or task-specific prompt engineering can hinder their generalization. We propose UPRISE (Universal Prompt Retrieval for Improving zero-Shot Evaluation), which tunes a lightweight and versatile retriever that automatically retrieves prompts for a given zero-shot task input. Specifically, we demonstrate universality in a cross-task and cross-model scenario: the retriever is tuned on diverse tasks, but tested on unseen task types; we use a small frozen LLM, GPT-Neo-2.7B, for tuning the retriever, but test the retriever on different LLMs of much larger scales, such as BLOOM-7.1B, OPT-66B and GPT3-175B. Additionally, we show that UPRISE mitigates the hallucination problem in our experiments with ChatGPT, suggesting its potential to improve even the strongest LLMs. Our model and code are available at https://github.com/microsoft/LMOps.
The prompt-based learning paradigm, which bridges the gap between pre-training and fine-tuning, achieves state-of-the-art performance on several NLP tasks, particularly in few-shot settings. Despite being widely applied, prompt-based learning is vulnerable to backdoor attacks. Textual backdoor attacks are designed to introduce targeted vulnerabilities into models by poisoning a subset of training samples through trigger injection and label modification. However, they suffer from flaws such as abnormal natural language expressions resulting from the trigger and incorrect labeling of poisoned samples. In this study, we propose ProAttack, a novel and efficient method for performing clean-label backdoor attacks based on the prompt, which uses the prompt itself as a trigger. Our method does not require external triggers and ensures correct labeling of poisoned samples, improving the stealthy nature of the backdoor attack. With extensive experiments on rich-resource and few-shot text classification tasks, we empirically validate ProAttack’s competitive performance in textual backdoor attacks. Notably, in the rich-resource setting, ProAttack achieves state-of-the-art attack success rates in the clean-label backdoor attack benchmark without external triggers.
Discovering fine-grained categories from coarsely labeled data is a practical and challenging task, which can bridge the gap between the demand for fine-grained analysis and the high annotation cost. Previous works mainly focus on instance-level discrimination to learn low-level features, but ignore semantic similarities between data, which may prevent these models learning compact cluster representations. In this paper, we propose \textit{Denoised Neighborhood Aggregation} (DNA), a self-supervised framework that encodes semantic structures of data into the embedding space. Specifically, we retrieve \textit{k}-nearest neighbors of a query as its positive keys to capture semantic similarities between data and then aggregate information from the neighbors to learn compact cluster representations, which can make fine-grained categories more separatable. However, the retrieved neighbors can be noisy and contain many false-positive keys, which can degrade the quality of learned embeddings. To cope with this challenge, we propose three principles to filter out these false neighbors for better representation learning. Furthermore, we theoretically justify that the learning objective of our framework is equivalent to a clustering loss, which can capture semantic similarities between data to form compact fine-grained clusters. Extensive experiments on three benchmark datasets show that our method can retrieve more accurate neighbors (21.31% accuracy improvement) and outperform state-of-the-art models by a large margin (average 9.96% improvement on three metrics). Our code and data are available at https://github.com/Lackel/DNA.
Is aesthetic impact different from beauty? Is visual salience a reflection of its capacity for effective communication? We present Impressions, a novel dataset through which to investigate the semiotics of images, and how specific visual features and design choices can elicit specific emotions, thoughts and beliefs. We posit that the impactfulness of an image extends beyond formal definitions of aesthetics, to its success as a communicative act, where style contributes as much to meaning formation as the subject matter. We also acknowledge that existing Image Captioning datasets are not designed to empower state-of-the-art architectures to model potential human impressions or interpretations of images. To fill this need, we design an annotation task heavily inspired by image analysis techniques in the Visual Arts to collect 1,440 image-caption pairs and 4,320 unique annotations exploring impact, pragmatic image description, impressions and aesthetic design choices. We show that existing multimodal image captioning and conditional generation models struggle to simulate plausible human responses to images. However, this dataset significantly improves their ability to model impressions and aesthetic evaluations of images through fine-tuning and few-shot adaptation.
The term translationese describes the set of linguistic features unique to translated texts, which appear regardless of translation quality. Though automatic classifiers designed to distinguish translated texts achieve high accuracy and prior work has identified common hallmarks of translationese, human accuracy of identifying translated text is understudied. In this work, we perform a human evaluation of English original/translated texts in order to explore raters’ ability to classify texts as being original or translated English and the features that lead a rater to judge text as being translated. Ultimately, we find that, regardless of the annotators’ native language or the source language of the text, annotators are unable to distinguish translations from original English texts and also have low agreement. Our results provide critical insight into work in translation studies and context for assessments of translationese classifiers.
Large language models (LLMs) like ChatGPT can be expensive to train, deploy, and use for specific natural language generation tasks such as text summarization and for certain domains. A promising alternative is to fine-tune relatively smaller language models (LMs) on a particular task using high-quality, in-domain datasets. However, it can be prohibitively expensive to get such high-quality training data. This issue has been mitigated by generating weakly supervised data via knowledge distillation (KD) of LLMs. We propose a three-step approach to distill ChatGPT and fine-tune smaller LMs for summarizing forum conversations. More specifically, we design a method to selectively sample a large unannotated corpus of forum conversation using a semantic similarity metric. Then, we use the same metric to retrieve suitable prompts for ChatGPT from a small annotated validation set in the same domain. The generated dataset is then filtered to remove low-quality instances. Our proposed select-prompt-filter KD approach leads to significant improvements of up to 6.6 ROUGE-2 score by leveraging sufficient in-domain pseudo-labeled data over a standard KD approach given the same size of training data.
Large Language Models (LLMs) have been observed to encode and perpetuate harmful associations present in the training data. We propose a theoretically grounded framework called StereoMap to gain insights into their perceptions of how demographic groups have been viewed by society. The framework is grounded in the Stereotype Content Model (SCM); a well-established theory from psychology. According to SCM, stereotypes are not all alike. Instead, the dimensions of Warmth and Competence serve as the factors that delineate the nature of stereotypes. Based on the SCM theory, StereoMap maps LLMs’ perceptions of social groups (defined by socio-demographic features) using the dimensions of Warmth and Competence. Furthermore, the framework enables the investigation of keywords and verbalizations of reasoning of LLMs’ judgments to uncover underlying factors influencing their perceptions. Our results show that LLMs exhibit a diverse range of perceptions towards these groups, characterized by mixed evaluations along the dimensions of Warmth and Competence. Furthermore, analyzing the reasonings of LLMs, our findings indicate that LLMs demonstrate an awareness of social disparities, often stating statistical data and research findings to support their reasoning. This study contributes to the understanding of how LLMs perceive and represent social groups, shedding light on their potential biases and the perpetuation of harmful associations.