2024
pdf
bib
abs
Effective Large Language Model Adaptation for Improved Grounding and Citation Generation
Xi Ye
|
Ruoxi Sun
|
Sercan Arik
|
Tomas Pfister
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
Large language models (LLMs) have achieved remarkable advancements in natural language understanding and generation. However, one major issue towards their widespread deployment in the real world is that they can generate “hallucinated” answers that are not factual.Towards this end, this paper focuses on improving LLMs by grounding their responses in retrieved passages and by providing citations. We propose a new framework, AGREE, Adaptation for GRounding EnhancEment, that improves the grounding from a holistic perspective. Our framework tunes LLMs to self-ground the claims in their responses and provide accurate citations to retrieved documents. This tuning on top of the pre-trained LLMs requires well-grounded responses (with citations) for paired queries, for which we introduce a method that can automatically construct such data from unlabeled queries. The self-grounding capability of tuned LLMs further grants them a test-time adaptation (TTA) capability that can actively retrieve passages to support the claims that have not been grounded, which iteratively improves the responses of LLMs. Across five datasets and two LLMs, our results show that the proposed tuning-based framework generates superior grounded responses with more accurate citations compared to prompting-based approaches and post-hoc citing-based approaches.
pdf
bib
abs
CodecLM: Aligning Language Models with Tailored Synthetic Data
Zifeng Wang
|
Chun-Liang Li
|
Vincent Perot
|
Long Le
|
Jin Miao
|
Zizhao Zhang
|
Chen-Yu Lee
|
Tomas Pfister
Findings of the Association for Computational Linguistics: NAACL 2024
Instruction tuning has emerged as the key in aligning large language models (LLMs) with specific task instructions, thereby mitigating the discrepancy between the next-token prediction objective and users’ actual goals. To reduce the labor and time cost to collect or annotate data by humans, researchers start to explore the use of LLMs to generate instruction-aligned synthetic data. Recent works focus on generating diverse instructions and applying LLM to increase instruction complexity, often neglecting downstream use cases. It remains unclear how to tailor high-quality data to elicit better instruction-following abilities in different target instruction distributions and LLMs. To this end, we introduce CodecLM, a general framework for adaptively generating high-quality synthetic data for LLM alignment with different downstream instruction distributions and LLMs. Drawing on the Encode-Decode principles, we use LLMs as codecs to guide the data generation process. We first encode seed instructions into metadata, which are concise keywords generated on-the-fly to capture the target instruction distribution, and then decode metadata to create tailored instructions. We also introduce Self-Rubrics and Contrastive Filtering during decoding to tailor data-efficient samples. Extensive experiments on four open-domain instruction following benchmarks validate the effectiveness of CodecLM over the current state-of-the-arts.
pdf
bib
abs
CaLM: Contrasting Large and Small Language Models to Verify Grounded Generation
I-Hung Hsu
|
Zifeng Wang
|
Long Le
|
Lesly Miculicich
|
Nanyun Peng
|
Chen-Yu Lee
|
Tomas Pfister
Findings of the Association for Computational Linguistics ACL 2024
Grounded generation aims to equip language models (LMs) with the ability to produce more credible and accountable responses by accurately citing verifiable sources. However, existing methods, by either feeding LMs with raw or preprocessed materials, remain prone to errors. To address this, we introduce CaLM, a novel verification framework. CaLM leverages the insight that a robust grounded response should be consistent with information derived solely from its cited sources. Our framework empowers smaller LMs, which rely less on parametric memory and excel at processing relevant information given a query, to validate the output of larger LMs. Larger LM responses that closely align with the smaller LMs’ output, which relies exclusively on cited documents, are verified. Responses showing discrepancies are iteratively refined through a feedback loop. Experiments on three open-domain question-answering datasets demonstrate significant performance gains of 1.5% to 7% absolute average without any required model fine-tuning.
pdf
bib
abs
TextGenSHAP: Scalable Post-Hoc Explanations in Text Generation with Long Documents
James Enouen
|
Hootan Nakhost
|
Sayna Ebrahimi
|
Sercan Arik
|
Yan Liu
|
Tomas Pfister
Findings of the Association for Computational Linguistics ACL 2024
Large language models (LLMs) have attracted great interest in many real-world applications; however, their “black-box” nature necessitates scalable and faithful explanations. Shapley values have matured as an explainability method for deep learning, but extending them to LLMs is difficult due to long input contexts and autoregressive output generation. We introduce , an efficient post-hoc explanation method incorporating LLM-specific techniques, which leads to significant runtime improvements: token-level explanations in minutes not hours, and document-level explanations within seconds. We demonstrate how such explanations can improve end-to-end performance of retrieval augmented generation by localizing important words within long documents and reranking passages collected by retrieval systems. On various open-domain question answering benchmarks, we show TextGenSHAP improves the retrieval recall and prediction accuracy significantly.
pdf
bib
abs
Found in the middle: Calibrating Positional Attention Bias Improves Long Context Utilization
Cheng-Yu Hsieh
|
Yung-Sung Chuang
|
Chun-Liang Li
|
Zifeng Wang
|
Long Le
|
Abhishek Kumar
|
James Glass
|
Alexander Ratner
|
Chen-Yu Lee
|
Ranjay Krishna
|
Tomas Pfister
Findings of the Association for Computational Linguistics ACL 2024
Large language models (LLMs), even when specifically trained to process long input contexts, struggle to capture relevant information located in the middle of their input. This phenomenon has been known as the lost-in-the-middle problem. In this work, we make three contributions. First, we set out to understand the factors that cause this phenomenon. In doing so, we establish a connection between lost-in-the-middle to LLMs’ intrinsic attention bias: LLMs exhibit an U-shaped attention bias where the tokens at the beginning and at the end of its input receive higher attention, regardless of their relevance. Second, we mitigate this positional bias through a calibration mechanism, found-in-the-middle, that allows the model to attend to contexts faithfully according to their relevance, even though when they are in the middle. Third, we show found-in-the-middle not only achieves better performance in locating relevant information within a long context, but also eventually leads to improved retrieval-augmented generation (RAG) performance across various tasks, outperforming existing methods by up to 10 percentage point. These findings open up future directions in understanding LLM attention bias and its potential consequences.
pdf
bib
abs
Search-Adaptor: Embedding Customization for Information Retrieval
Jinsung Yoon
|
Yanfei Chen
|
Sercan Arik
|
Tomas Pfister
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Embeddings extracted by pre-trained Large Language Models (LLMs) have significant potential to improve information retrieval and search. Beyond the zero-shot setup in which they are being conventionally used, being able to take advantage of the information from the relevant query-corpus paired data can further boost the LLM capabilities. In this paper, we propose a novel method, Search-Adaptor, for customizing LLMs for information retrieval in an efficient and robust way. Search-Adaptor modifies the embeddings generated by pre-trained LLMs, and can be integrated with any LLM, including those only available via prediction APIs. On multiple English, multilingual, and multimodal retrieval datasets, we show consistent and significant performance benefits for Search-Adaptor – e.g., more than 5% improvements for Google Embedding APIs in nDCG@10 averaged over 14 BEIR datasets.
2023
pdf
bib
abs
Better Zero-Shot Reasoning with Self-Adaptive Prompting
Xingchen Wan
|
Ruoxi Sun
|
Hanjun Dai
|
Sercan Arik
|
Tomas Pfister
Findings of the Association for Computational Linguistics: ACL 2023
Modern large language models (LLMs) have demonstrated impressive capabilities at sophisticated tasks, often through step-by-step reasoning similar to humans. This is made possible by their strong few- and zero-shot abilities – they can effectively learn from a handful of handcrafted, completed responses (“in-context examples”), or are prompted to reason spontaneously through specially designed triggers. Nonetheless, some limitations have been observed. First, performance in the few-shot setting is sensitive to the choice of the examples, whose design requires significant human effort. Moreover, given the diverse downstream tasks of LLMs, it may be difficult or laborious to handcraft per-task labels. Second, while the zero-shot setting does not require handcrafting, its performance is limited due to the lack of guidance to the LLMs. To address these limitations, we propose Consistency-based Self-adaptive Prompting (COSP), a novel prompt design method for LLMs. Requiring neither handcrafted responses nor ground-truth labels, COSP selects and builds the set of examples from the LLM zero-shot outputs via carefully designed criteria combining consistency, diversity and repetition. In the zero-shot setting for three different LLMs, we show that using only LLM predictions, COSP significantly improves performance up to 15% compared to zero-shot baselines and matches or exceeds few-shot baselines at a range of reasoning tasks.
pdf
bib
abs
QueryForm: A Simple Zero-shot Form Entity Query Framework
Zifeng Wang
|
Zizhao Zhang
|
Jacob Devlin
|
Chen-Yu Lee
|
Guolong Su
|
Hao Zhang
|
Jennifer Dy
|
Vincent Perot
|
Tomas Pfister
Findings of the Association for Computational Linguistics: ACL 2023
Zero-shot transfer learning for document understanding is a crucial yet under-investigated scenario to help reduce the high cost involved in annotating document entities. We present a novel query-based framework, QueryForm, that extracts entity values from form-like documents in a zero-shot fashion. QueryForm contains a dual prompting mechanism that composes both the document schema and a specific entity type into a query, which is used to prompt a Transformer model to perform a single entity extraction task. Furthermore, we propose to leverage large-scale query-entity pairs generated from form-like webpages with weak HTML annotations to pre-train QueryForm. By unifying pre-training and fine-tuning into the same query-based framework, QueryForm enables models to learn from structured documents containing various entities and layouts, leading to better generalization to target document types without the need for target-specific training data. QueryForm sets new state-of-the-art average F1 score on both the XFUND (+4.6% 10.1%) and the Payment (+3.2% 9.5%) zero-shot benchmark, with a smaller model size and no additional image input.
pdf
bib
abs
Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes
Cheng-Yu Hsieh
|
Chun-Liang Li
|
Chih-kuan Yeh
|
Hootan Nakhost
|
Yasuhisa Fujii
|
Alex Ratner
|
Ranjay Krishna
|
Chen-Yu Lee
|
Tomas Pfister
Findings of the Association for Computational Linguistics: ACL 2023
Deploying large language models (LLMs) is challenging because they are memory inefficient and compute-intensive for practical applications. In reaction, researchers train smaller task-specific models by either finetuning with human labels or distilling using LLM-generated labels. However, finetuning and distillation require large amounts of training data to achieve comparable performance to LLMs. We introduce Distilling step-by-step, a new mechanism that (a) trains smaller models that outperform LLMs, and (b) achieves so by leveraging less training data needed by finetuning or distillation. Our method extracts LLM rationales as additional supervision for training small models within a multi-task framework. We present three findings across 4 NLP benchmarks: First, compared to both finetuning and distillation, our mechanism achieves better performance with much fewer labeled/unlabeled training examples. Second, compared to few-shot prompted LLMs, we achieve better performance using substantially smaller model sizes. Third, we reduce both the model size and the amount of data required to outperform LLMs; our finetuned 770M T5 model outperforms the few-shot prompted 540B PaLM model using only 80% of available data on a benchmark, whereas standard finetuning the same T5 model struggles to match even by using 100% of the dataset.
pdf
bib
abs
SQLPrompt: In-Context Text-to-SQL with Minimal Labeled Data
Ruoxi Sun
|
Sercan Arik
|
Rajarishi Sinha
|
Hootan Nakhost
|
Hanjun Dai
|
Pengcheng Yin
|
Tomas Pfister
Findings of the Association for Computational Linguistics: EMNLP 2023
Text-to-SQL aims to automate the process of generating SQL queries on a database from natural language text. In this work, we propose “SQLPrompt”, tailored to improve the few-shot prompting capabilities of Text-to-SQL for Large Language Models (LLMs). Our methods include innovative prompt design, execution-based consistency decoding strategy which selects the SQL with the most consistent execution outcome among other SQL proposals, and a method that aims to improve performance by diversifying the SQL proposals during consistency selection with different prompt designs (“MixPrompt”) and foundation models (“MixLLMs”). We show that SQLPrompt outperforms previous approaches for in-context learning with zero labeled data by a large margin, closing the gap with finetuning state-of-the-art with thousands of labeled data.
pdf
bib
abs
Adaptation with Self-Evaluation to Improve Selective Prediction in LLMs
Jiefeng Chen
|
Jinsung Yoon
|
Sayna Ebrahimi
|
Sercan Arik
|
Tomas Pfister
|
Somesh Jha
Findings of the Association for Computational Linguistics: EMNLP 2023
Large language models (LLMs) have recently shown great advances in a variety of tasks, including natural language understanding and generation. However, their use in high-stakes decision-making scenarios is still limited due to the potential for errors. *Selective prediction* is a technique that can be used to improve the reliability of the LLMs by allowing them to abstain from making predictions when they are unsure of the answer. In this work, we propose a novel framework for adaptation with self-evaluation to improve the selective prediction performance of LLMs. Our framework is based on the idea of using parameter-efficient tuning to adapt the LLM to the specific task at hand while improving its ability to perform self-evaluation. We evaluate our method on a variety of question-answering (QA) datasets and show that it outperforms state-of-the-art selective prediction methods. For example, on the CoQA benchmark, our method improves the AUACC from 91.23% to 92.63% and improves the AUROC from 74.61% to 80.25%.
pdf
bib
abs
Universal Self-Adaptive Prompting
Xingchen Wan
|
Ruoxi Sun
|
Hootan Nakhost
|
Hanjun Dai
|
Julian Eisenschlos
|
Sercan Arik
|
Tomas Pfister
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
A hallmark of modern large language models (LLMs) is their impressive general zero-shot and few-shot abilities, often elicited through in-context learning (ICL) via prompting. However, while highly coveted and being the most general, zero-shot performances in LLMs are still typically weaker due to the lack of guidance and the difficulty of applying existing automatic prompt design methods in general tasks when ground-truth labels are unavailable. In this study, we address this by presenting Universal Self-Adaptive Prompting (USP), an automatic prompt design approach specifically tailored for zero-shot learning (while compatible with few-shot). Requiring only a small amount of unlabeled data and an inference-only LLM, USP is highly versatile: to achieve universal prompting, USP categorizes a possible NLP task into one of the three possible task types and then uses a corresponding selector to select the most suitable queries and zero-shot model-generated responses as pseudo-demonstrations, thereby generalizing ICL to the zero-shot setup in a fully automated way. We evaluate USP with PaLM and PaLM 2 models and demonstrate performances that are considerably stronger than standard zero-shot baselines and often comparable to or even superior to few-shot baselines across more than 40 natural language understanding, natural language generation, and reasoning tasks.
pdf
bib
abs
FormNetV2: Multimodal Graph Contrastive Learning for Form Document Information Extraction
Chen-Yu Lee
|
Chun-Liang Li
|
Hao Zhang
|
Timothy Dozat
|
Vincent Perot
|
Guolong Su
|
Xiang Zhang
|
Kihyuk Sohn
|
Nikolay Glushnev
|
Renshen Wang
|
Joshua Ainslie
|
Shangbang Long
|
Siyang Qin
|
Yasuhisa Fujii
|
Nan Hua
|
Tomas Pfister
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
The recent advent of self-supervised pre-training techniques has led to a surge in the use of multimodal learning in form document understanding. However, existing approaches that extend the mask language modeling to other modalities require careful multi-task tuning, complex reconstruction target designs, or additional pre-training data. In FormNetV2, we introduce a centralized multimodal graph contrastive learning strategy to unify self-supervised pre-training for all modalities in one loss. The graph contrastive objective maximizes the agreement of multimodal representations, providing a natural interplay for all modalities without special customization. In addition, we extract image features within the bounding box that joins a pair of tokens connected by a graph edge, capturing more targeted visual cues without loading a sophisticated and separately pre-trained image embedder. FormNetV2 establishes new state-of-the-art performance on FUNSD, CORD, SROIE and Payment benchmarks with a more compact model size.
2022
pdf
bib
abs
FormNet: Structural Encoding beyond Sequential Modeling in Form Document Information Extraction
Chen-Yu Lee
|
Chun-Liang Li
|
Timothy Dozat
|
Vincent Perot
|
Guolong Su
|
Nan Hua
|
Joshua Ainslie
|
Renshen Wang
|
Yasuhisa Fujii
|
Tomas Pfister
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Sequence modeling has demonstrated state-of-the-art performance on natural language and document understanding tasks. However, it is challenging to correctly serialize tokens in form-like documents in practice due to their variety of layout patterns. We propose FormNet, a structure-aware sequence model to mitigate the suboptimal serialization of forms. First, we design Rich Attention that leverages the spatial relationship between tokens in a form for more precise attention score calculation. Second, we construct Super-Tokens for each word by embedding representations from their neighboring tokens through graph convolutions. FormNet therefore explicitly recovers local syntactic information that may have been lost during serialization. In experiments, FormNet outperforms existing methods with a more compact model size and less pre-training data, establishing new state-of-the-art performance on CORD, FUNSD and Payment benchmarks.
2021
pdf
bib
abs
ROPE: Reading Order Equivariant Positional Encoding for Graph-based Document Information Extraction
Chen-Yu Lee
|
Chun-Liang Li
|
Chu Wang
|
Renshen Wang
|
Yasuhisa Fujii
|
Siyang Qin
|
Ashok Popat
|
Tomas Pfister
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
Natural reading orders of words are crucial for information extraction from form-like documents. Despite recent advances in Graph Convolutional Networks (GCNs) on modeling spatial layout patterns of documents, they have limited ability to capture reading orders of given word-level node representations in a graph. We propose Reading Order Equivariant Positional Encoding (ROPE), a new positional encoding technique designed to apprehend the sequential presentation of words in documents. ROPE generates unique reading order codes for neighboring words relative to the target word given a word-level graph connectivity. We study two fundamental document entity extraction tasks including word labeling and word grouping on the public FUNSD dataset and a large-scale payment dataset. We show that ROPE consistently improves existing GCNs with a margin up to 8.4% F1-score.