An open challenge in recent machine learning is about how to improve the reasoning capability of large language models (LLMs) in a black-box setting, i.e., without access to detailed information such as output token probabilities. Existing approaches either rely on accessibility (which is often unrealistic) or involve significantly increased train- and inference-time costs. This paper addresses those limitations or shortcomings by proposing a novel approach, namely CoBB (Correct for improving QA reasoning of Black-Box LLMs). It uses a trained adaptation model to perform a seq2seq mapping from the often-imperfect reasonings of the original black-box LLM to the correct or improved reasonings. Specifically, the adaptation model is initialized with a relatively small open-source LLM and adapted over a collection of sub-sampled training pairs. To select the representative pairs of correct and incorrect reasonings, we formulated the dataset construction as an optimization problem that minimizes the statistical divergence between the sampled subset and the entire collection, and solved it via a genetic algorithm. We then train the adaptation model over the sampled pairs by contrasting the likelihoods of correct and incorrect reasonings. Our experimental results demonstrate that CoBB significantly improves reasoning accuracy across various QA benchmarks, compared to the best-performing adaptation baselines.
Large Multimodal Models (LMM) are built across modalities and the misalignment between two modalities can result in “hallucination”, generating textual outputs that are not grounded by the multimodal information in context. To address the multimodal misalignment issue, we adapt the Reinforcement Learning from Human Feedback (RLHF) from the text domain to the vision-language alignment, where human annotators are asked to compare two responses and pinpoint the more hallucinated one, and the vision-language model is trained to maximize the simulated human rewards. We propose a new alignment algorithm called Factually Augmented RLHF that augments the reward model with additional factual information such as image captions and ground-truth multi-choice options, which alleviates the reward hacking phenomenon in RLHF and further improves the performance. We also enhance the GPT-4-generated training data (for vision instruction tuning) with previously available human-written image-text pairs to improve the general capabilities of our model. To evaluate the proposed approach in real-world scenarios, we develop a new evaluation benchmark MMHAL-BENCH with a special focus on penalizing hallucinations. As the first LMM trained with RLHF, our approach achieves remarkable improvement on the LLaVA-Bench dataset with the 96% performance level of the text-only GPT-4 (while previous best methods can only achieve the 87% level), and an improvement of 60% on MMHAL-BENCH over other baselines.
The remarkable performance of large language models (LLMs) in zero-shot language understanding has garnered significant attention.However, employing LLMs for large-scale inference or domain-specific fine-tuning requires immense computational resources due to their substantial model size. To overcome these limitations, we introduce a novel method, namely GenCo, which leverages the strong generative power of LLMs to assist in training a smaller and more adaptable language model. In our method, an LLM plays an important role in the self-training loop of a smaller model in two important ways. Firstly, we utilize an LLM to generate multiple augmented texts for each input instance to enhance its semantic meaning for better understanding. Secondly, we additionally generate high-quality training instances conditioned on predicted labels, ensuring the generated texts are relevant to the labels. In this way, GenCo not only corrects the errors of predicted labels during self-training but also eliminates the need for extensive unlabeled texts. In our experiments, GenCo outperforms previous state-of-the-art methods when only limited (<5% of original) in-domain text data is available. Notably, our approach surpasses Alpaca-7B with human instructions, highlighting the significance of self-training.
We present PESCO, a novel contrastive learning framework that substantially improves the performance of zero-shot text classification. We formulate text classification as a neural text retrieval problem where each document is treated as a query, and the system learns the mapping from each query to the relevant class labels by (1) adding prompts to enhance label retrieval, and (2) using retrieved labels to enrich the training set in a self-training loop of contrastive learning. PESCO achieves state-of-the-art performance on four benchmark text classification datasets. On DBpedia, we achieve 98.5% accuracy without any labeled data, which is close to the fully-supervised result. Extensive experiments and analyses show all the components of PESCO are necessary for improving the performance of zero-shot text classification.
Extreme Multi-label Text Classification (XMTC) has been a tough challenge in machine learning research and applications due to the sheer sizes of the label spaces and the severe data scarcity problem associated with the long tail of rare labels in highly skewed distributions. This paper addresses the challenge of tail label prediction by leveraging the power of dense neural retrieval model in mapping input documents (as queries) to relevant label descriptions. To further enhance the quality of label descriptions, we propose to generate pseudo label descriptions from a trained bag-of-words (BoW) classifier, which demonstrates better classification performance under severe scarce data conditions. The proposed approach achieves the state-of-the-art (SOTA) performance of overall label prediction on XMTC benchmark datasets and especially outperforms the SOTA models in the tail label prediction. We also provide a theoretical analysis for relating the BoW and neural models w.r.t. performance lower bound.
How much success in Knowledge Graph Completion (KGC) would translate into the performance enhancement in downstream tasks is an important question that has not been studied in depth. In this paper, we introduce a novel benchmark, namely CompleQA, to comprehensively assess the influence of representative KGC methods on Knowledge Graph Question Answering (KGQA), one of the most important downstream applications. This benchmark includes a knowledge graph with 3 million triplets across 5 distinct domains, coupled with over 5000 question-answering pairs and a completion dataset that is well-aligned with these questions. Our evaluation of four well-known KGC methods in combination with two state-of-the-art KGQA systems shows that effective KGC can significantly mitigate the impact of knowledge graph incompleteness on question-answering performance. Surprisingly, we also find that the best-performing KGC method(s) does not necessarily lead to the best QA results, underscoring the need to consider downstream applications when doing KGC.
Despite the remarkable ability of large language models (LMs) to comprehend and generate language, they have a tendency to hallucinate and create factually inaccurate output. Augmenting LMs by retrieving information from external knowledge resources is one promising solution. Most existing retrieval augmented LMs employ a retrieve-and-generate setup that only retrieves information once based on the input. This is limiting, however, in more general scenarios involving generation of long texts, where continually gathering information throughout generation is essential. In this work, we provide a generalized view of active retrieval augmented generation, methods that actively decide when and what to retrieve across the course of the generation. We propose Forward-Looking Active REtrieval augmented generation (FLARE), a generic method which iteratively uses a prediction of the upcoming sentence to anticipate future content, which is then utilized as a query to retrieve relevant documents to regenerate the sentence if it contains low-confidence tokens. We test FLARE along with baselines comprehensively over 4 long-form knowledge-intensive generation tasks/datasets. FLARE achieves superior or competitive performance on all tasks, demonstrating the effectiveness of our method.
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%
Current Open-Domain Question Answering (ODQA) models typically include a retrieving module and a reading module, where the retriever selects potentially relevant passages from open-source documents for a given question, and the reader produces an answer based on the retrieved passages. The recently proposed Fusion-in-Decoder (FiD) framework is a representative example, which is built on top of a dense passage retriever and a generative reader, achieving the state-of-the-art performance. In this paper we further improve the FiD approach by introducing a knowledge-enhanced version, namely KG-FiD. Our new model uses a knowledge graph to establish the structural relationship among the retrieved passages, and a graph neural network (GNN) to re-rank the passages and select only a top few for further processing. Our experiments on common ODQA benchmark datasets (Natural Questions and TriviaQA) demonstrate that KG-FiD can achieve comparable or better performance in answer prediction than FiD, with less than 40% of the computation cost.
We address the general task of structured commonsense reasoning: given a natural language input, the goal is to generate a graph such as an event or a reasoning-graph.To employ large language models (LMs) for this task, existing approaches ‘serialize’ the output graph as a flat list of nodes and edges.Although feasible, these serialized graphs strongly deviate from the natural language corpora that LMs were pre-trained on, hindering LMs from generating them correctly. In this paper, we show that when we instead frame structured commonsense reasoning tasks as code generation tasks, pre-trained LMs of code are better structured commonsense reasoners than LMs of natural language, even when the downstream task does not involve source code at all.We demonstrate our approach across three diverse structured commonsense reasoning tasks. In all these natural language tasks, we show that using our approach, a code generation LM (codex) outperforms natural-LMs that are fine-tuned on the target task (T5) and other strong LMs such as GPT-3 in the few-shot setting.
Large LMs such as GPT-3 are powerful, but can commit mistakes that are obvious to humans. For example, GPT-3 would mistakenly interpret “What word is similar to good?” to mean a homophone, while the user intended a synonym. Our goal is to effectively correct such errors via user interactions with the system but without retraining, which will be prohibitively costly. We pair GPT-3 with a growing memory of recorded cases where the model misunderstood the user’s intents, along with user feedback for clarification. Such a memory allows our system to produce enhanced prompts for any new query based on the user feedback for error correction on similar cases in the past. On four tasks (two lexical tasks, two advanced ethical reasoning tasks), we show how a (simulated) user can interactively teach a deployed GPT-3, substantially increasing its accuracy over the queries with different kinds of misunderstandings by the GPT-3. Our approach is a step towards the low-cost utility enhancement for very large pre-trained LMs.
Conditional set generation learns a mapping from an input sequence of tokens to a set. Several NLP tasks, such as entity typing and dialogue emotion tagging, are instances of set generation. Seq2Seq models are a popular choice to model set generation but they treat a set as a sequence and do not fully leverage its key properties, namely order-invariance and cardinality. We propose a novel algorithm for effectively sampling informative orders over the combinatorial space of label orders. Further, we jointly model the set cardinality and output by listing the set size as the first element and taking advantage of the autoregressive factorization used by Seq2Seq models. Our method is a model-independent data augmentation approach that endows any Seq2Seq model with the signals of order-invariance and cardinality. Training a Seq2Seq model on this new augmented data (without any additional annotations), gets an average relative improvement of 20% for four benchmarks datasets across models spanning from BART-base, T5-11B, and GPT-3. We will release all code and data upon acceptance.
Large language models (LMs), while powerful, are not immune to mistakes, but can be difficult to retrain. Our goal is for an LM to continue to improve after deployment, without retraining, using feedback from the user. Our approach pairs an LM with (i) a growing memory of cases where the user identified an output error and provided general feedback on how to correct it (ii) a corrector model, trained to translate this general feedback into specific edits to repair the model output. Given a new, unseen input, our model can then use feedback from similar, past cases to repair output errors that may occur. We instantiate our approach using an existing, fixed model for script generation, that takes a goal (e.g., “bake a cake”) and generates a partially ordered sequence of actions to achieve that goal, sometimes containing errors. Our memory-enhanced system, , learns to apply user feedback to repair such errors (up to 30 points improvement), while making a start at avoiding similar past mistakes on new, unseen examples (up to 7 points improvement in a controlled setting). This is a first step towards strengthening deployed models, potentially broadening their utility. Our code and data is available at https://github.com/allenai/interscript
Predicting the effects of unexpected situations is an important reasoning task, e.g., would cloudy skies help or hinder plant growth? Given a context, the goal of such situational reasoning is to elicit the consequences of a new situation (st) that arises in that context. We propose CURIE, a method to iteratively build a graph of relevant consequences explicitly in a structured situational graph (st graph) using natural language queries over a finetuned language model. Across multiple domains, CURIE generates st graphs that humans find relevant and meaningful in eliciting the consequences of a new situation (75% of the graphs were judged correct by humans). We present a case study of a situation reasoning end task (WIQA-QA), where simply augmenting their input with st graphs improves accuracy by 3 points. We show that these improvements mainly come from a hard subset of the data, that requires background knowledge and multi-hop reasoning.
This paper presents the first study on using large-scale pre-trained language models for automated generation of an event-level temporal graph for a document. Despite the huge success of neural pre-training methods in NLP tasks, its potential for temporal reasoning over event graphs has not been sufficiently explored. Part of the reason is the difficulty in obtaining large training corpora with human-annotated events and temporal links. We address this challenge by using existing IE/NLP tools to automatically generate a large quantity (89,000) of system-produced document-graph pairs, and propose a novel formulation of the contextualized graph generation problem as a sequence-to-sequence mapping task. These strategies enable us to leverage and fine-tune pre-trained language models on the system-induced training data for the graph generation task. Our experiments show that our approach is highly effective in generating structurally and semantically valid graphs. Further, evaluation on a challenging hand-labeled, out-of-domain corpus shows that our method outperforms the closest existing method by a large margin on several metrics. We also show a downstream application of our approach by adapting it to answer open-ended temporal questions in a reading comprehension setting.
Defeasible reasoning is the mode of reasoning where conclusions can be overturned by taking into account new evidence. Existing cognitive science literature on defeasible reasoning suggests that a person forms a “mental model” of the problem scenario before answering questions. Our research goal asks whether neural models can similarly benefit from envisioning the question scenario before answering a defeasible query. Our approach is, given a question, to have a model first create a graph of relevant influences, and then leverage that graph as an additional input when answering the question. Our system, CURIOUS, achieves a new state-of-the-art on three different defeasible reasoning datasets. This result is significant as it illustrates that performance can be improved by guiding a system to “think about” a question and explicitly model the scenario, rather than answering reflexively.
This paper introduces a new task of politeness transfer which involves converting non-polite sentences to polite sentences while preserving the meaning. We also provide a dataset of more than 1.39 instances automatically labeled for politeness to encourage benchmark evaluations on this new task. We design a tag and generate pipeline that identifies stylistic attributes and subsequently generates a sentence in the target style while preserving most of the source content. For politeness as well as five other transfer tasks, our model outperforms the state-of-the-art methods on automatic metrics for content preservation, with a comparable or better performance on style transfer accuracy. Additionally, our model surpasses existing methods on human evaluations for grammaticality, meaning preservation and transfer accuracy across all the six style transfer tasks. The data and code is located at https://github.com/tag-and-generate.
Natural Language Processing (NLP) has recently achieved great success by using huge pre-trained models with hundreds of millions of parameters. However, these models suffer from heavy model sizes and high latency such that they cannot be deployed to resource-limited mobile devices. In this paper, we propose MobileBERT for compressing and accelerating the popular BERT model. Like the original BERT, MobileBERT is task-agnostic, that is, it can be generically applied to various downstream NLP tasks via simple fine-tuning. Basically, MobileBERT is a thin version of BERT_LARGE, while equipped with bottleneck structures and a carefully designed balance between self-attentions and feed-forward networks. To train MobileBERT, we first train a specially designed teacher model, an inverted-bottleneck incorporated BERT_LARGE model. Then, we conduct knowledge transfer from this teacher to MobileBERT. Empirical studies show that MobileBERT is 4.3x smaller and 5.5x faster than BERT_BASE while achieving competitive results on well-known benchmarks. On the natural language inference tasks of GLUE, MobileBERT achieves a GLUE score of 77.7 (0.6 lower than BERT_BASE), and 62 ms latency on a Pixel 4 phone. On the SQuAD v1.1/v2.0 question answering task, MobileBERT achieves a dev F1 score of 90.0/79.2 (1.5/2.1 higher than BERT_BASE).
Knowledge Graph Completion (KGC) aims at automatically predicting missing links for large-scale knowledge graphs. A vast number of state-of-the-art KGC techniques have got published at top conferences in several research fields, including data mining, machine learning, and natural language processing. However, we notice that several recent papers report very high performance, which largely outperforms previous state-of-the-art methods. In this paper, we find that this can be attributed to the inappropriate evaluation protocol used by them and propose a simple evaluation protocol to address this problem. The proposed protocol is robust to handle bias in the model, which can substantially affect the final results. We conduct extensive experiments and report performance of several existing methods using our protocol. The reproducible code has been made publicly available.
Given the complexity of combinations of tasks, languages, and domains in natural language processing (NLP) research, it is computationally prohibitive to exhaustively test newly proposed models on each possible experimental setting. In this work, we attempt to explore the possibility of gaining plausible judgments of how well an NLP model can perform under an experimental setting, without actually training or testing the model. To do so, we build regression models to predict the evaluation score of an NLP experiment given the experimental settings as input. Experimenting on~9 different NLP tasks, we find that our predictors can produce meaningful predictions over unseen languages and different modeling architectures, outperforming reasonable baselines as well as human experts. %we represent experimental settings using an array of features. Going further, we outline how our predictor can be used to find a small subset of representative experiments that should be run in order to obtain plausible predictions for all other experimental settings.
Pre-trained contextual representations like BERT have achieved great success in natural language processing. However, the sentence embeddings from the pre-trained language models without fine-tuning have been found to poorly capture semantic meaning of sentences. In this paper, we argue that the semantic information in the BERT embeddings is not fully exploited. We first reveal the theoretical connection between the masked language model pre-training objective and the semantic similarity task theoretically, and then analyze the BERT sentence embeddings empirically. We find that BERT always induces a non-smooth anisotropic semantic space of sentences, which harms its performance of semantic similarity. To address this issue, we propose to transform the anisotropic sentence embedding distribution to a smooth and isotropic Gaussian distribution through normalizing flows that are learned with an unsupervised objective. Experimental results show that our proposed BERT-flow method obtains significant performance gains over the state-of-the-art sentence embeddings on a variety of semantic textual similarity tasks. The code is available at https://github.com/bohanli/BERT-flow.
Transformers have a potential of learning longer-term dependency, but are limited by a fixed-length context in the setting of language modeling. We propose a novel neural architecture Transformer-XL that enables learning dependency beyond a fixed length without disrupting temporal coherence. It consists of a segment-level recurrence mechanism and a novel positional encoding scheme. Our method not only enables capturing longer-term dependency, but also resolves the context fragmentation problem. As a result, Transformer-XL learns dependency that is 80% longer than RNNs and 450% longer than vanilla Transformers, achieves better performance on both short and long sequences, and is up to 1,800+ times faster than vanilla Transformers during evaluation. Notably, we improve the state-of-the-art results of bpc/perplexity to 0.99 on enwiki8, 1.08 on text8, 18.3 on WikiText-103, 21.8 on One Billion Word, and 54.5 on Penn Treebank (without finetuning). When trained only on WikiText-103, Transformer-XL manages to generate reasonably coherent, novel text articles with thousands of tokens. Our code, pretrained models, and hyperparameters are available in both Tensorflow and PyTorch.
When trained effectively, the Variational Autoencoder (VAE) is both a powerful language model and an effective representation learning framework. In practice, however, VAEs are trained with the evidence lower bound (ELBO) as a surrogate objective to the intractable marginal data likelihood. This approach to training yields unstable results, frequently leading to a disastrous local optimum known as posterior collapse. In this paper, we investigate a simple fix for posterior collapse which yields surprisingly effective results. The combination of two known heuristics, previously considered only in isolation, substantially improves held-out likelihood, reconstruction, and latent representation learning when compared with previous state-of-the-art methods. More interestingly, while our experiments demonstrate superiority on these principle evaluations, our method obtains a worse ELBO. We use these results to argue that the typical surrogate objective for VAEs may not be sufficient or necessarily appropriate for balancing the goals of representation learning and data distribution modeling.
Definition extraction has been a popular topic in NLP research for well more than a decade, but has been historically limited to well-defined, structured, and narrow conditions. In reality, natural language is messy, and messy data requires both complex solutions and data that reflects that reality. In this paper, we present a robust English corpus and annotation schema that allows us to explore the less straightforward examples of term-definition structures in free and semi-structured text.
The use of machine learning for NLP generally requires resources for training. Tasks performed in a low-resource language usually rely on labeled data in another, typically resource-rich, language. However, there might not be enough labeled data even in a resource-rich language such as English. In such cases, one approach is to use a hand-crafted approach that utilizes only a small bilingual dictionary with minimal manual verification to create distantly supervised data. Another is to explore typical machine learning techniques, for example adversarial training of bilingual word representations. We find that in event-type detection task—the task to classify [parts of] documents into a fixed set of labels—they give about the same performance. We explore ways in which the two methods can be complementary and also see how to best utilize a limited budget for manual annotation to maximize performance gain.
Cross-lingual transfer of word embeddings aims to establish the semantic mappings among words in different languages by learning the transformation functions over the corresponding word embedding spaces. Successfully solving this problem would benefit many downstream tasks such as to translate text classification models from resource-rich languages (e.g. English) to low-resource languages. Supervised methods for this problem rely on the availability of cross-lingual supervision, either using parallel corpora or bilingual lexicons as the labeled data for training, which may not be available for many low resource languages. This paper proposes an unsupervised learning approach that does not require any cross-lingual labeled data. Given two monolingual word embedding spaces for any language pair, our algorithm optimizes the transformation functions in both directions simultaneously based on distributional matching as well as minimizing the back-translation losses. We use a neural network implementation to calculate the Sinkhorn distance, a well-defined distributional similarity measure, and optimize our objective through back-propagation. Our evaluation on benchmark datasets for bilingual lexicon induction and cross-lingual word similarity prediction shows stronger or competitive performance of the proposed method compared to other state-of-the-art supervised and unsupervised baseline methods over many language pairs.
We present RACE, a new dataset for benchmark evaluation of methods in the reading comprehension task. Collected from the English exams for middle and high school Chinese students in the age range between 12 to 18, RACE consists of near 28,000 passages and near 100,000 questions generated by human experts (English instructors), and covers a variety of topics which are carefully designed for evaluating the students’ ability in understanding and reasoning. In particular, the proportion of questions that requires reasoning is much larger in RACE than that in other benchmark datasets for reading comprehension, and there is a significant gap between the performance of the state-of-the-art models (43%) and the ceiling human performance (95%). We hope this new dataset can serve as a valuable resource for research and evaluation in machine comprehension. The dataset is freely available at http://www.cs.cmu.edu/~glai1/data/race/and the code is available at https://github.com/qizhex/RACE_AR_baselines.
Cross-lingual text classification(CLTC) is the task of classifying documents written in different languages into the same taxonomy of categories. This paper presents a novel approach to CLTC that builds on model distillation, which adapts and extends a framework originally proposed for model compression. Using soft probabilistic predictions for the documents in a label-rich language as the (induced) supervisory labels in a parallel corpus of documents, we train classifiers successfully for new languages in which labeled training data are not available. An adversarial feature adaptation technique is also applied during the model training to reduce distribution mismatch. We conducted experiments on two benchmark CLTC datasets, treating English as the source language and German, French, Japan and Chinese as the unlabeled target languages. The proposed approach had the advantageous or comparable performance of the other state-of-art methods.
Event extraction has become one of the most important topics in information extraction, but to date, there is very limited work on leveraging cross-lingual training to boost performance. We propose a new event extraction approach that trains on multiple languages using a combination of both language-dependent and language-independent features, with particular focus on the case where target domain training data is of very limited size. We show empirically that multilingual training can boost performance for the tasks of event trigger extraction and event argument extraction on the Chinese ACE 2005 dataset.