Alert button
Picture for Dawei Yin

Dawei Yin

Alert button

Explainability for Large Language Models: A Survey

Sep 17, 2023
Haiyan Zhao, Hanjie Chen, Fan Yang, Ninghao Liu, Huiqi Deng, Hengyi Cai, Shuaiqiang Wang, Dawei Yin, Mengnan Du

Figure 1 for Explainability for Large Language Models: A Survey
Figure 2 for Explainability for Large Language Models: A Survey
Figure 3 for Explainability for Large Language Models: A Survey
Figure 4 for Explainability for Large Language Models: A Survey

Large language models (LLMs) have demonstrated impressive capabilities in natural language processing. However, their internal mechanisms are still unclear and this lack of transparency poses unwanted risks for downstream applications. Therefore, understanding and explaining these models is crucial for elucidating their behaviors, limitations, and social impacts. In this paper, we introduce a taxonomy of explainability techniques and provide a structured overview of methods for explaining Transformer-based language models. We categorize techniques based on the training paradigms of LLMs: traditional fine-tuning-based paradigm and prompting-based paradigm. For each paradigm, we summarize the goals and dominant approaches for generating local explanations of individual predictions and global explanations of overall model knowledge. We also discuss metrics for evaluating generated explanations, and discuss how explanations can be leveraged to debug models and improve performance. Lastly, we examine key challenges and emerging opportunities for explanation techniques in the era of LLMs in comparison to conventional machine learning models.

Viaarxiv icon

Information Retrieval Meets Large Language Models: A Strategic Report from Chinese IR Community

Jul 27, 2023
Qingyao Ai, Ting Bai, Zhao Cao, Yi Chang, Jiawei Chen, Zhumin Chen, Zhiyong Cheng, Shoubin Dong, Zhicheng Dou, Fuli Feng, Shen Gao, Jiafeng Guo, Xiangnan He, Yanyan Lan, Chenliang Li, Yiqun Liu, Ziyu Lyu, Weizhi Ma, Jun Ma, Zhaochun Ren, Pengjie Ren, Zhiqiang Wang, Mingwen Wang, Ji-Rong Wen, Le Wu, Xin Xin, Jun Xu, Dawei Yin, Peng Zhang, Fan Zhang, Weinan Zhang, Min Zhang, Xiaofei Zhu

Figure 1 for Information Retrieval Meets Large Language Models: A Strategic Report from Chinese IR Community

The research field of Information Retrieval (IR) has evolved significantly, expanding beyond traditional search to meet diverse user information needs. Recently, Large Language Models (LLMs) have demonstrated exceptional capabilities in text understanding, generation, and knowledge inference, opening up exciting avenues for IR research. LLMs not only facilitate generative retrieval but also offer improved solutions for user understanding, model evaluation, and user-system interactions. More importantly, the synergistic relationship among IR models, LLMs, and humans forms a new technical paradigm that is more powerful for information seeking. IR models provide real-time and relevant information, LLMs contribute internal knowledge, and humans play a central role of demanders and evaluators to the reliability of information services. Nevertheless, significant challenges exist, including computational costs, credibility concerns, domain-specific limitations, and ethical considerations. To thoroughly discuss the transformative impact of LLMs on IR research, the Chinese IR community conducted a strategic workshop in April 2023, yielding valuable insights. This paper provides a summary of the workshop's outcomes, including the rethinking of IR's core values, the mutual enhancement of LLMs and IR, the proposal of a novel IR technical paradigm, and open challenges.

* 17 pages 
Viaarxiv icon

Exploring the Potential of Large Language Models (LLMs) in Learning on Graphs

Jul 10, 2023
Zhikai Chen, Haitao Mao, Hang Li, Wei Jin, Hongzhi Wen, Xiaochi Wei, Shuaiqiang Wang, Dawei Yin, Wenqi Fan, Hui Liu, Jiliang Tang

Figure 1 for Exploring the Potential of Large Language Models (LLMs) in Learning on Graphs
Figure 2 for Exploring the Potential of Large Language Models (LLMs) in Learning on Graphs
Figure 3 for Exploring the Potential of Large Language Models (LLMs) in Learning on Graphs
Figure 4 for Exploring the Potential of Large Language Models (LLMs) in Learning on Graphs

Learning on Graphs has attracted immense attention due to its wide real-world applications. The most popular pipeline for learning on graphs with textual node attributes primarily relies on Graph Neural Networks (GNNs), and utilizes shallow text embedding as initial node representations, which has limitations in general knowledge and profound semantic understanding. In recent years, Large Language Models (LLMs) have been proven to possess extensive common knowledge and powerful semantic comprehension abilities that have revolutionized existing workflows to handle text data. In this paper, we aim to explore the potential of LLMs in graph machine learning, especially the node classification task, and investigate two possible pipelines: LLMs-as-Enhancers and LLMs-as-Predictors. The former leverages LLMs to enhance nodes' text attributes with their massive knowledge and then generate predictions through GNNs. The latter attempts to directly employ LLMs as standalone predictors. We conduct comprehensive and systematical studies on these two pipelines under various settings. From comprehensive empirical results, we make original observations and find new insights that open new possibilities and suggest promising directions to leverage LLMs for learning on graphs.

* fix some minor typos and errors 
Viaarxiv icon

Evaluating Graph Neural Networks for Link Prediction: Current Pitfalls and New Benchmarking

Jun 18, 2023
Juanhui Li, Harry Shomer, Haitao Mao, Shenglai Zeng, Yao Ma, Neil Shah, Jiliang Tang, Dawei Yin

Figure 1 for Evaluating Graph Neural Networks for Link Prediction: Current Pitfalls and New Benchmarking
Figure 2 for Evaluating Graph Neural Networks for Link Prediction: Current Pitfalls and New Benchmarking
Figure 3 for Evaluating Graph Neural Networks for Link Prediction: Current Pitfalls and New Benchmarking
Figure 4 for Evaluating Graph Neural Networks for Link Prediction: Current Pitfalls and New Benchmarking

Link prediction attempts to predict whether an unseen edge exists based on only a portion of edges of a graph. A flurry of methods have been introduced in recent years that attempt to make use of graph neural networks (GNNs) for this task. Furthermore, new and diverse datasets have also been created to better evaluate the effectiveness of these new models. However, multiple pitfalls currently exist that hinder our ability to properly evaluate these new methods. These pitfalls mainly include: (1) Lower than actual performance on multiple baselines, (2) A lack of a unified data split and evaluation metric on some datasets, and (3) An unrealistic evaluation setting that uses easy negative samples. To overcome these challenges, we first conduct a fair comparison across prominent methods and datasets, utilizing the same dataset and hyperparameter search settings. We then create a more practical evaluation setting based on a Heuristic Related Sampling Technique (HeaRT), which samples hard negative samples via multiple heuristics. The new evaluation setting helps promote new challenges and opportunities in link prediction by aligning the evaluation with real-world situations. Our implementation and data are available at https://github.com/Juanhui28/HeaRT

Viaarxiv icon

I^3 Retriever: Incorporating Implicit Interaction in Pre-trained Language Models for Passage Retrieval

Jun 04, 2023
Qian Dong, Yiding Liu, Qingyao Ai, Haitao Li, Shuaiqiang Wang, Yiqun Liu, Dawei Yin, Shaoping Ma

Figure 1 for I^3 Retriever: Incorporating Implicit Interaction in Pre-trained Language Models for Passage Retrieval
Figure 2 for I^3 Retriever: Incorporating Implicit Interaction in Pre-trained Language Models for Passage Retrieval
Figure 3 for I^3 Retriever: Incorporating Implicit Interaction in Pre-trained Language Models for Passage Retrieval
Figure 4 for I^3 Retriever: Incorporating Implicit Interaction in Pre-trained Language Models for Passage Retrieval

Passage retrieval is a fundamental task in many information systems, such as web search and question answering, where both efficiency and effectiveness are critical concerns. In recent years, neural retrievers based on pre-trained language models (PLM), such as dual-encoders, have achieved huge success. Yet, studies have found that the performance of dual-encoders are often limited due to the neglecting of the interaction information between queries and candidate passages. Therefore, various interaction paradigms have been proposed to improve the performance of vanilla dual-encoders. Particularly, recent state-of-the-art methods often introduce late-interaction during the model inference process. However, such late-interaction based methods usually bring extensive computation and storage cost on large corpus. Despite their effectiveness, the concern of efficiency and space footprint is still an important factor that limits the application of interaction-based neural retrieval models. To tackle this issue, we incorporate implicit interaction into dual-encoders, and propose I^3 retriever. In particular, our implicit interaction paradigm leverages generated pseudo-queries to simulate query-passage interaction, which jointly optimizes with query and passage encoders in an end-to-end manner. It can be fully pre-computed and cached, and its inference process only involves simple dot product operation of the query vector and passage vector, which makes it as efficient as the vanilla dual encoders. We conduct comprehensive experiments on MSMARCO and TREC2019 Deep Learning Datasets, demonstrating the I^3 retriever's superiority in terms of both effectiveness and efficiency. Moreover, the proposed implicit interaction is compatible with special pre-training and knowledge distillation for passage retrieval, which brings a new state-of-the-art performance.

* 10 pages 
Viaarxiv icon

Pretrained Language Model based Web Search Ranking: From Relevance to Satisfaction

Jun 02, 2023
Canjia Li, Xiaoyang Wang, Dongdong Li, Yiding Liu, Yu Lu, Shuaiqiang Wang, Zhicong Cheng, Simiu Gu, Dawei Yin

Figure 1 for Pretrained Language Model based Web Search Ranking: From Relevance to Satisfaction
Figure 2 for Pretrained Language Model based Web Search Ranking: From Relevance to Satisfaction
Figure 3 for Pretrained Language Model based Web Search Ranking: From Relevance to Satisfaction
Figure 4 for Pretrained Language Model based Web Search Ranking: From Relevance to Satisfaction

Search engine plays a crucial role in satisfying users' diverse information needs. Recently, Pretrained Language Models (PLMs) based text ranking models have achieved huge success in web search. However, many state-of-the-art text ranking approaches only focus on core relevance while ignoring other dimensions that contribute to user satisfaction, e.g., document quality, recency, authority, etc. In this work, we focus on ranking user satisfaction rather than relevance in web search, and propose a PLM-based framework, namely SAT-Ranker, which comprehensively models different dimensions of user satisfaction in a unified manner. In particular, we leverage the capacities of PLMs on both textual and numerical inputs, and apply a multi-field input that modularizes each dimension of user satisfaction as an input field. Overall, SAT-Ranker is an effective, extensible, and data-centric framework that has huge potential for industrial applications. On rigorous offline and online experiments, SAT-Ranker obtains remarkable gains on various evaluation sets targeting different dimensions of user satisfaction. It is now fully deployed online to improve the usability of our search engine.

Viaarxiv icon

Semantic-Enhanced Differentiable Search Index Inspired by Learning Strategies

May 24, 2023
Yubao Tang, Ruqing Zhang, Jiafeng Guo, Jiangui Chen, Zuowei Zhu, Shuaiqiang Wang, Dawei Yin, Xueqi Cheng

Figure 1 for Semantic-Enhanced Differentiable Search Index Inspired by Learning Strategies
Figure 2 for Semantic-Enhanced Differentiable Search Index Inspired by Learning Strategies
Figure 3 for Semantic-Enhanced Differentiable Search Index Inspired by Learning Strategies
Figure 4 for Semantic-Enhanced Differentiable Search Index Inspired by Learning Strategies

Recently, a new paradigm called Differentiable Search Index (DSI) has been proposed for document retrieval, wherein a sequence-to-sequence model is learned to directly map queries to relevant document identifiers. The key idea behind DSI is to fully parameterize traditional ``index-retrieve'' pipelines within a single neural model, by encoding all documents in the corpus into the model parameters. In essence, DSI needs to resolve two major questions: (1) how to assign an identifier to each document, and (2) how to learn the associations between a document and its identifier. In this work, we propose a Semantic-Enhanced DSI model (SE-DSI) motivated by Learning Strategies in the area of Cognitive Psychology. Our approach advances original DSI in two ways: (1) For the document identifier, we take inspiration from Elaboration Strategies in human learning. Specifically, we assign each document an Elaborative Description based on the query generation technique, which is more meaningful than a string of integers in the original DSI; and (2) For the associations between a document and its identifier, we take inspiration from Rehearsal Strategies in human learning. Specifically, we select fine-grained semantic features from a document as Rehearsal Contents to improve document memorization. Both the offline and online experiments show improved retrieval performance over prevailing baselines.

* Accepted by KDD 2023 
Viaarxiv icon

Unconfounded Propensity Estimation for Unbiased Ranking

May 18, 2023
Dan Luo, Lixin Zou, Qingyao Ai, Zhiyu Chen, Chenliang Li, Dawei Yin, Brian D. Davison

Figure 1 for Unconfounded Propensity Estimation for Unbiased Ranking
Figure 2 for Unconfounded Propensity Estimation for Unbiased Ranking
Figure 3 for Unconfounded Propensity Estimation for Unbiased Ranking
Figure 4 for Unconfounded Propensity Estimation for Unbiased Ranking

The goal of unbiased learning to rank (ULTR) is to leverage implicit user feedback for optimizing learning-to-rank systems. Among existing solutions, automatic ULTR algorithms that jointly learn user bias models (i.e., propensity models) with unbiased rankers have received a lot of attention due to their superior performance and low deployment cost in practice. Despite their theoretical soundness, the effectiveness is usually justified under a weak logging policy, where the ranking model can barely rank documents according to their relevance to the query. However, when the logging policy is strong, e.g., an industry-deployed ranking policy, the reported effectiveness cannot be reproduced. In this paper, we first investigate ULTR from a causal perspective and uncover a negative result: existing ULTR algorithms fail to address the issue of propensity overestimation caused by the query-document relevance confounder. Then, we propose a new learning objective based on backdoor adjustment and highlight its differences from conventional propensity models, which reveal the prevalence of propensity overestimation. On top of that, we introduce a novel propensity model called Logging-Policy-aware Propensity (LPP) model and its distinctive two-step optimization strategy, which allows for the joint learning of LPP and ranking models within the automatic ULTR framework, and actualize the unconfounded propensity estimation for ULTR. Extensive experiments on two benchmarks demonstrate the effectiveness and generalizability of the proposed method.

* 11 pages, 5 figures 
Viaarxiv icon