Search Results for author:
Found 89 papers, 45 papers with code
LexEval: A Comprehensive Chinese Legal Benchmark for Evaluating Large Language Models
Applying existing LLMs to legal systems without careful evaluation of their potential and limitations could pose significant risks in legal practice.
LeKUBE: A Legal Knowledge Update BEnchmark
Existing benchmarks for evaluating knowledge update methods are mostly designed for the open domain and cannot address the specific challenges of the legal domain, such as the nuanced application of new legal knowledge, the complexity and lengthiness of legal regulations, and the intricate nature of legal reasoning.
Mitigating Entity-Level Hallucination in Large Language Models
To tackle this challenge, this paper proposes Dynamic Retrieval Augmentation based on hallucination Detection (DRAD) as a novel method to detect and mitigate hallucinations in LLMs.
Prompt Refinement with Image Pivot for Text-to-Image Generation
Such a prompt refinement process is analogous to translating the prompt from "user languages" into "system languages".
STARD: A Chinese Statute Retrieval Dataset with Real Queries Issued by Non-professionals
Statute retrieval aims to find relevant statutory articles for specific queries.
EEG-ImageNet: An Electroencephalogram Dataset and Benchmarks with Image Visual Stimuli of Multi-Granularity Labels
Experiments with several commonly used models show that the best models can achieve object classification with accuracy around 60% and image reconstruction with two-way identification around 64%.
Investigating the Robustness of Counterfactual Learning to Rank Models: A Reproducibility Study
Counterfactual learning to rank (CLTR) has attracted extensive attention in the IR community for its ability to leverage massive logged user interaction data to train ranking models.
EEG-SVRec: An EEG Dataset with User Multidimensional Affective Engagement Labels in Short Video Recommendation
To address these challenges and provide a more comprehensive understanding of user affective experience and cognitive activity, we propose EEG-SVRec, the first EEG dataset with User Multidimensional Affective Engagement Labels in Short Video Recommendation.
Towards an In-Depth Comprehension of Case Relevance for Better Legal Retrieval
Legal retrieval techniques play an important role in preserving the fairness and equality of the judicial system.
DELTA: Pre-train a Discriminative Encoder for Legal Case Retrieval via Structural Word Alignment
Most of the existing works focus on improving the representation ability for the contextualized embedding of the [CLS] token and calculate relevance using textual semantic similarity.
Capability-aware Prompt Reformulation Learning for Text-to-Image Generation
Our in-depth analysis of these logs reveals that user prompt reformulation is heavily dependent on the individual user's capability, resulting in significant variance in the quality of reformulation pairs.
BLADE: Enhancing Black-box Large Language Models with Small Domain-Specific Models
However, general LLMs, which are developed on open-domain data, may lack the domain-specific knowledge essential for tasks in vertical domains, such as legal, medical, etc.
Scaling Laws For Dense Retrieval
In this study, we investigate whether the performance of dense retrieval models follows the scaling law as other neural models.
Sequential Recommendation with Latent Relations based on Large Language Model
Different from previous relation-aware models that rely on predefined rules, we propose to leverage the Large Language Model (LLM) to provide new types of relations and connections between items.
A Situation-aware Enhancer for Personalized Recommendation
In this paper, we provide a new perspective that takes situations as the preconditions for users' interactions.
Common Sense Enhanced Knowledge-based Recommendation with Large Language Model
Knowledge-based recommendation models effectively alleviate the data sparsity issue leveraging the side information in the knowledge graph, and have achieved considerable performance.
Improving Legal Case Retrieval with Brain Signals
Traditional feedback signal such as clicks is too coarse to use as they do not reflect any fine-grained relevance information.
Evaluation Ethics of LLMs in Legal Domain
In recent years, the utilization of large language models for natural language dialogue has gained momentum, leading to their widespread adoption across various domains.
DRAGIN: Dynamic Retrieval Augmented Generation based on the Information Needs of Large Language Models
Our framework is specifically designed to make decisions on when and what to retrieve based on the LLM's real-time information needs during the text generation process.
Unsupervised Real-Time Hallucination Detection based on the Internal States of Large Language Models
Hallucinations in large language models (LLMs) refer to the phenomenon of LLMs producing responses that are coherent yet factually inaccurate.
Gender Biased Legal Case Retrieval System on Users' Decision Process
Gender of the defendants in both the task and relevant cases was edited to statistically measure the effect of gender bias in the legal case search results on participants' perceptions.
Query Augmentation by Decoding Semantics from Brain Signals
If the quality of the initially retrieved documents is low, then the effectiveness of query augmentation would be limited as well.
PRE: A Peer Review Based Large Language Model Evaluator
Existing paradigms rely on either human annotators or model-based evaluators to evaluate the performance of LLMs on different tasks.
Wikiformer: Pre-training with Structured Information of Wikipedia for Ad-hoc Retrieval
With the development of deep learning and natural language processing techniques, pre-trained language models have been widely used to solve information retrieval (IR) problems.
Relevance Feedback with Brain Signals
To explore the effectiveness of brain signals in the context of RF, we propose a novel RF framework that combines BCI-based relevance feedback with pseudo-relevance signals and implicit signals to improve the performance of document re-ranking.
Language Generation from Brain Recordings
Inspired by recent research that revealed associations between the brain and the large computational language models, we propose a generative language BCI that utilizes the capacity of a large language model (LLM) jointly with a semantic brain decoder to directly generate language from functional magnetic resonance imaging (fMRI) input.
Caseformer: Pre-training for Legal Case Retrieval Based on Inter-Case Distinctions
Legal case retrieval aims to help legal workers find relevant cases related to their cases at hand, which is important for the guarantee of fairness and justice in legal judgments.
LeCaRDv2: A Large-Scale Chinese Legal Case Retrieval Dataset
However, the development of legal case retrieval technologies in the Chinese legal system is restricted by three problems in existing datasets: limited data size, narrow definitions of legal relevance, and naive candidate pooling strategies used in data sampling.
Investigating the Influence of Legal Case Retrieval Systems on Users' Decision Process
Given a specific query case, legal case retrieval systems aim to retrieve a set of case documents relevant to the case at hand.
Unsupervised Large Language Model Alignment for Information Retrieval via Contrastive Feedback
Large language models (LLMs) have demonstrated remarkable capabilities across various research domains, including the field of Information Retrieval (IR).
GNN4EEG: A Benchmark and Toolkit for Electroencephalography Classification with Graph Neural Network
Recognizing this shortfall, there has been a burgeoning interest in recent years in harnessing the potential of Graph Neural Networks (GNN) to exploit the topological information by modeling features selected from each EEG channel in a graph structure.
An Intent Taxonomy of Legal Case Retrieval
Through a laboratory user study, we reveal significant differences in user behavior and satisfaction under different search intents in legal case retrieval.
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.
I^3 Retriever: Incorporating Implicit Interaction in Pre-trained Language Models for Passage Retrieval
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.
Mitigating Exploitation Bias in Learning to Rank with an Uncertainty-aware Empirical Bayes Approach
While previous studies have demonstrated the effectiveness of using user behavior signals (e. g., clicks) as both features and labels of LTR algorithms, we argue that existing LTR algorithms that indiscriminately treat behavior and non-behavior signals in input features could lead to suboptimal performance in practice.
FARA: Future-aware Ranking Algorithm for Fairness Optimization
However, we find that most existing fair ranking methods adopt greedy algorithms that only optimize rankings for the next immediate session or request.
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.
THUIR@COLIEE 2023: More Parameters and Legal Knowledge for Legal Case Entailment
This paper describes the approach of the THUIR team at the COLIEE 2023 Legal Case Entailment task.
THUIR@COLIEE 2023: Incorporating Structural Knowledge into Pre-trained Language Models for Legal Case Retrieval
Legal case retrieval techniques play an essential role in modern intelligent legal systems.
CaseEncoder: A Knowledge-enhanced Pre-trained Model for Legal Case Encoding
In the data sampling phase, we enhance the quality of the training data by utilizing fine-grained law article information to guide the selection of positive and negative examples.
THUIR at WSDM Cup 2023 Task 1: Unbiased Learning to Rank
This paper introduces the approaches we have used to participate in the WSDM Cup 2023 Task 1: Unbiased Learning to Rank.
Constructing Tree-based Index for Efficient and Effective Dense Retrieval
Unfortunately, while ANN can improve the efficiency of DR models, it usually comes with a significant price on retrieval performance.
SAILER: Structure-aware Pre-trained Language Model for Legal Case Retrieval
Moreover, in contrast to the general retrieval, the relevance in the legal domain is sensitive to key legal elements.
An In-depth Investigation of User Response Simulation for Conversational Search
Our goal is to supplement existing work with an insightful hand-analysis of unsolved challenges by the baseline and propose our solutions.
Metric-agnostic Ranking Optimization
To address this question, we conduct formal analysis on the limitation of existing ranking optimization techniques and describe three research tasks in \textit{Metric-agnostic Ranking Optimization}.
Reward-free Policy Imitation Learning for Conversational Search
In this paper, we propose a reward-free conversation policy imitation learning framework, which can train a conversation policy without annotated conversation data or manually designed rewards.
Towards Better Web Search Performance: Pre-training, Fine-tuning and Learning to Rank
This paper describes the approach of the THUIR team at the WSDM Cup 2023 Pre-training for Web Search task.
Zero-shot Clarifying Question Generation for Conversational Search
In this work, we innovatively explore generating clarifying questions in a zero-shot setting to overcome the cold start problem and we propose a constrained clarifying question generation system which uses both question templates and query facets to guide the effective and precise question generation.
Counterfactual Editing for Search Result Explanation
Next, we formulate a suite of desiderata for counterfactual explanation in SeRE task and corresponding automatic metrics.
Marginal-Certainty-aware Fair Ranking Algorithm
In MCFair, we first develop a ranking objective that includes uncertainty, fairness, and user utility.
Hard Negatives or False Negatives: Correcting Pooling Bias in Training Neural Ranking Models
When sampling top-ranked results (excluding the labeled positives) as negatives from a stronger retriever, the performance of the learned NRM becomes even worse.
Reinforcement Learning to Rank with Coarse-grained Labels
The results on simulated coarse-grained labeled dataset show that while using coarse-grained labels to train an RL model for LTR tasks still can not outperform traditional approaches using fine-grained labels, it still achieve somewhat promising results and is potentially helpful for future research in LTR.
Disentangled Modeling of Domain and Relevance for Adaptable Dense Retrieval
By making the REM and DAMs disentangled, DDR enables a flexible training paradigm in which REM is trained with supervision once and DAMs are trained with unsupervised data.
Model-based Unbiased Learning to Rank
Existing methods in unbiased learning to rank typically rely on click modeling or inverse propensity weighting (IPW).
Learning to Rank Rationales for Explainable Recommendation
Seeing this gap, we propose a model named Semantic-Enhanced Bayesian Personalized Explanation Ranking (SE-BPER) to effectively combine the interaction information and semantic information.
Vertical Allocation-based Fair Exposure Amortizing in Ranking
Result ranking often affects consumer satisfaction as well as the amount of exposure each item receives in the ranking services.
Towards Better Understanding of User Satisfaction in Open-Domain Conversational Search
This raises the question of how to accurately model user satisfaction in conversational search scenarios.
Simulating and Modeling the Risk of Conversational Search
These works assume asking clarifying questions is a safe alternative to retrieving results.
Model-agnostic vs. Model-intrinsic Interpretability for Explainable Product Search
In this paper, we study how to construct effective explainable product search by comparing model-agnostic explanation paradigms with model-intrinsic paradigms and analyzing the important factors that determine the performance of product search explanations.
ULTRA: An Unbiased Learning To Rank Algorithm Toolbox
Our toolbox is an important resource for researchers to conduct experiments on ULTR algorithms with different configurations as well as testing their own algorithms with the supported features.
Asking Clarifying Questions Based on Negative Feedback in Conversational Search
To quickly identify user intent and reduce effort during interactions, we propose an intent clarification task based on yes/no questions where the system needs to ask the correct question about intents within the fewest conversation turns.
Understanding the Effectiveness of Reviews in E-commerce Top-N Recommendation
We find that models utilizing only review information can not achieve better performances than vanilla implicit-feedback matrix factorization method.
A Neural Passage Model for Ad-hoc Document Retrieval
Traditional statistical retrieval models often treat each document as a whole.
Maximizing Marginal Fairness for Dynamic Learning to Rank
Rankings, especially those in search and recommendation systems, often determine how people access information and how information is exposed to people.
A Zero Attentive Relevance Matching Networkfor Review Modeling in Recommendation System
User and item reviews are valuable for the construction of recommender systems.
Controlling the Risk of Conversational Search via Reinforcement Learning
In this work, we propose a risk-aware conversational search agent model to balance the risk of answering user's query and asking clarifying questions.
A Hierarchical Self-attentive Convolution Network for Review Modeling in Recommendation Systems
Using reviews to learn user and item representations is important for recommender system.
Review Regularized Neural Collaborative Filtering
In recent years, text-aware collaborative filtering methods have been proposed to address essential challenges in recommendations such as data sparsity, cold start problem, and long-tail distribution.
Analysis of Multivariate Scoring Functions for Automatic Unbiased Learning to Rank
Because click data is often noisy and biased, a variety of methods have been proposed to construct unbiased learning to rank (ULTR) algorithms for the learning of unbiased ranking models.
E-commerce Recommendation with Weighted Expected Utility
In this paper, we interpret purchase utility as the satisfaction level a consumer gets from a product and propose a recommendation framework using EU to model consumers' behavioral patterns.
A Transformer-based Embedding Model for Personalized Product Search
Aware of these limitations, we propose a transformer-based embedding model (TEM) for personalized product search, which could dynamically control the influence of personalization by encoding the sequence of query and user's purchase history with a transformer architecture.
Unbiased Learning to Rank: Online or Offline?
While their definitions of \textit{unbiasness} are different, these two types of ULTR algorithms share the same goal -- to find the best models that rank documents based on their intrinsic relevance or utility.
Learning a Fine-Grained Review-based Transformer Model for Personalized Product Search
RTM conducts review-level matching between the user and item, where each review has a dynamic effect according to the context in the sequence.
SetRank: Learning a Permutation-Invariant Ranking Model for Information Retrieval
In learning-to-rank for information retrieval, a ranking model is automatically learned from the data and then utilized to rank the sets of retrieved documents.
Explainable Product Search with a Dynamic Relation Embedding Model
Specifically, we propose to model the "search and purchase" behavior as a dynamic relation between users and items, and create a dynamic knowledge graph based on both the multi-relational product data and the context of the search session.
Conversational Product Search Based on Negative Feedback
So in this paper, we propose a conversational paradigm for product search driven by non-relevant items, based on which fine-grained feedback is collected and utilized to show better results in the next iteration.
A Zero Attention Model for Personalized Product Search
In this paper, we formulate the problem of personalized product search and conduct large-scale experiments with search logs sampled from a commercial e-commerce search engine.
A Deep Look into Neural Ranking Models for Information Retrieval
Ranking models lie at the heart of research on information retrieval (IR).
Revisiting Iterative Relevance Feedback for Document and Passage Retrieval
We conduct extensive experiments to analyze and compare IRF with the standard top-k RF framework on document and passage retrieval.
Learning Groupwise Multivariate Scoring Functions Using Deep Neural Networks
To overcome this limitation, we propose a new framework for multivariate scoring functions, in which the relevance score of a document is determined jointly by multiple documents in the list.
Learning Heterogeneous Knowledge Base Embeddings for Explainable Recommendation
Specifically, we propose a knowledge-base representation learning framework to embed heterogeneous entities for recommendation, and based on the embedded knowledge base, a soft matching algorithm is proposed to generate personalized explanations for the recommended items.
Ranked #3 on
Link Prediction
on Yelp
Unbiased Learning to Rank with Unbiased Propensity Estimation
We find that the problem of estimating a propensity model from click data is a dual problem of unbiased learning to rank.
Learning a Deep Listwise Context Model for Ranking Refinement
Specifically, we employ a recurrent neural network to sequentially encode the top results using their feature vectors, learn a local context model and use it to re-rank the top results.
Learning over Knowledge-Base Embeddings for Recommendation
In this work, we propose to reason over knowledge base embeddings for personalized recommendation.
aNMM: Ranking Short Answer Texts with Attention-Based Neural Matching Model
As an alternative to question answering methods based on feature engineering, deep learning approaches such as convolutional neural networks (CNNs) and Long Short-Term Memory Models (LSTMs) have recently been proposed for semantic matching of questions and answers.
Ranked #12 on
Question Answering
on TrecQA
A Deep Relevance Matching Model for Ad-hoc Retrieval
Specifically, our model employs a joint deep architecture at the query term level for relevance matching.
Ranked #14 on
Ad-Hoc Information Retrieval
on TREC Robust04
Joint Representation Learning for Top-N Recommendation with Heterogeneous Information Sources
In this framework, each type of information source (review text, product image, numerical rating, etc) is adopted to learn the corresponding user and item representations based on available (deep) representation learning architectures.
Adaptability of Neural Networks on Varying Granularity IR Tasks
Recent work in Information Retrieval (IR) using Deep Learning models has yielded state of the art results on a variety of IR tasks.
