Search Results for author:
Found 44 papers, 26 papers with code
Leveraging LLMs to Evaluate Usefulness of Document
We also apply the labels produced by our method to predict user satisfaction, with real-world experiments indicating that these labels substantially improve the performance of satisfaction prediction models.
LLM4Ranking: An Easy-to-use Framework of Utilizing Large Language Models for Document Reranking
Utilizing large language models (LLMs) for document reranking has been a popular and promising research direction in recent years, many studies are dedicated to improving the performance and efficiency of using LLMs for reranking.
Exploring Human-Like Thinking in Search Simulations with Large Language Models
As existing search datasets do not include users' thought processes, we conducted a user study to collect a new dataset enriched with users' explicit thinking.
How do Large Language Models Understand Relevance? A Mechanistic Interpretability Perspective
Recent studies have shown that large language models (LLMs) can assess relevance and support information retrieval (IR) tasks such as document ranking and relevance judgment generation.
PanguIR Technical Report for NTCIR-18 AEOLLM Task
To address these challenges, NTCIR-18 introduced the AEOLLM (Automatic Evaluation of LLMs) task, aiming to encourage reference-free evaluation methods that can overcome the limitations of existing approaches.
Evaluating Intelligence via Trial and Error
When the expectation and variance of failure counts are both finite, it signals the ability to consistently find solutions to new challenges, which we define as the Autonomous Level of intelligence.
Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning
Specifically, we present MMOA-RAG, a Multi-Module joint Optimization Algorithm for RAG, which employs multi-agent reinforcement learning to harmonize all agents' goals towards a unified reward, such as the F1 score of the final answer.
Research on the Proximity Relationships of Psychosomatic Disease Knowledge Graph Modules Extracted by Large Language Models
As social changes accelerate, the incidence of psychosomatic disorders has significantly increased, becoming a major challenge in global health issues.
BaichuanSEED: Sharing the Potential of ExtensivE Data Collection and Deduplication by Introducing a Competitive Large Language Model Baseline
The general capabilities of Large Language Models (LLM) highly rely on the composition and selection on extensive pretraining datasets, treated as commercial secrets by several institutions.
Mamba Retriever: Utilizing Mamba for Effective and Efficient Dense Retrieval
Experimental results show that (1) on the MS MARCO passage ranking dataset and BEIR, the Mamba Retriever achieves comparable or better effectiveness compared to Transformer-based retrieval models, and the effectiveness grows with the size of the Mamba model; (2) on the long-text LoCoV0 dataset, the Mamba Retriever can extend to longer text length than its pre-trained length after fine-tuning on retrieval task, and it has comparable or better effectiveness compared to other long-text retrieval models; (3) the Mamba Retriever has superior inference speed for long-text retrieval.
Towards Effective and Efficient Continual Pre-training of Large Language Models
To make the CPT approach more traceable, this paper presents a technical report for continually pre-training Llama-3 (8B), which significantly enhances the Chinese language ability and scientific reasoning ability of the backbone model.
Aligning Explanations for Recommendation with Rating and Feature via Maximizing Mutual Information
However, as current explanation generation methods are commonly trained with an objective to mimic existing user reviews, the generated explanations are often not aligned with the predicted ratings or some important features of the recommended items, and thus, are suboptimal in helping users make informed decision on the recommendation platform.
Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation
We conduct a series of well-designed experiments to highlight the following advantages of ToG-2: 1) ToG-2 tightly couples the processes of context retrieval and graph retrieval, deepening context retrieval via the KG while enabling reliable graph retrieval based on contexts; 2) it achieves deep and faithful reasoning in LLMs through an iterative knowledge retrieval process of collaboration between contexts and the KG; and 3) ToG-2 is training-free and plug-and-play compatible with various LLMs.
YuLan: An Open-source Large Language Model
This paper presents the development of YuLan, a series of open-source LLMs with $12$ billion parameters.
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".
Leveraging Passage Embeddings for Efficient Listwise Reranking with Large Language Models
To address these issues, in this paper, we propose PE-Rank, leveraging the single passage embedding as a good context compression for efficient listwise passage reranking.
TourRank: Utilizing Large Language Models for Documents Ranking with a Tournament-Inspired Strategy
However, several significant challenges still persist in LLMs for ranking: (1) LLMs are constrained by limited input length, precluding them from processing a large number of documents simultaneously; (2) The output document sequence is influenced by the input order of documents, resulting in inconsistent ranking outcomes; (3) Achieving a balance between cost and ranking performance is quite challenging.
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.
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.
Leveraging Large Language Models for Relevance Judgments in Legal Case Retrieval
Nonetheless, the method of employing a general large language model for reliable relevance judgments in legal case retrieval is yet to be thoroughly explored.
MA4DIV: Multi-Agent Reinforcement Learning for Search Result Diversification
The objective of search result diversification (SRD) is to ensure that selected documents cover as many different subtopics as possible.
An Analysis on Matching Mechanisms and Token Pruning for Late-interaction Models
Based on these findings, we then propose several simple document pruning methods to reduce the storage overhead and compare the effectiveness of different pruning methods on different late-interaction models.
USimAgent: Large Language Models for Simulating Search Users
However, the potential of using LLMs in simulating search behaviors has not yet been fully explored.
An Integrated Data Processing Framework for Pretraining Foundation Models
The ability of the foundation models heavily relies on large-scale, diverse, and high-quality pretraining data.
CoSearchAgent: A Lightweight Collaborative Search Agent with Large Language Models
Hence, to better support the research in collaborative search, in this demo, we propose CoSearchAgent, a lightweight collaborative search agent powered by LLMs.
Session-level Normalization and Click-through Data Enhancement for Session-based Evaluation
Besides, it infers session-level relevance labels based on implicit feedback.
CoAScore: Chain-of-Aspects Prompting for NLG Evaluation
Specifically, for a given aspect to evaluate, we first prompt the LLM to generate a chain of aspects that are relevant to the target aspect and could be useful for the evaluation.
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.
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.
PTDE: Personalized Training with Distilled Execution for Multi-Agent Reinforcement Learning
Furthermore, we introduce a novel paradigm named Personalized Training with Distilled Execution (PTDE), wherein agent-personalized global information is distilled into the agent's local information.
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.
Evaluating Interpolation and Extrapolation Performance of Neural Retrieval Models
For example, representation-based retrieval models perform almost as well as interaction-based retrieval models in terms of interpolation but not extrapolation.
Interacting with Non-Cooperative User: A New Paradigm for Proactive Dialogue Policy
To this end, we contribute to advance the study of the proactive dialogue policy to a more natural and challenging setting, i. e., interacting dynamically with users.
KuaiRec: A Fully-observed Dataset and Insights for Evaluating Recommender Systems
The progress of recommender systems is hampered mainly by evaluation as it requires real-time interactions between humans and systems, which is too laborious and expensive.
Interpreting Dense Retrieval as Mixture of Topics
Dense Retrieval (DR) reaches state-of-the-art results in first-stage retrieval, but little is known about the mechanisms that contribute to its success.
Learning Discrete Representations via Constrained Clustering for Effective and Efficient Dense Retrieval
However, the efficiency of most existing DR models is limited by the large memory cost of storing dense vectors and the time-consuming nearest neighbor search (NNS) in vector space.
POSSCORE: A Simple Yet Effective Evaluation of Conversational Search with Part of Speech Labelling
Conversational search systems, such as Google Assistant and Microsoft Cortana, provide a new search paradigm where users are allowed, via natural language dialogues, to communicate with search systems.
Jointly Optimizing Query Encoder and Product Quantization to Improve Retrieval Performance
Compared with previous DR models that use brute-force search, JPQ almost matches the best retrieval performance with 30x compression on index size.
Optimizing Dense Retrieval Model Training with Hard Negatives
ADORE replaces the widely-adopted static hard negative sampling method with a dynamic one to directly optimize the ranking performance.
THUIR@COLIEE-2020: Leveraging Semantic Understanding and Exact Matching for Legal Case Retrieval and Entailment
We participated in the two case law tasks, i. e., the legal case retrieval task and the legal case entailment task.
Learning To Retrieve: How to Train a Dense Retrieval Model Effectively and Efficiently
Through this process, it teaches the DR model how to retrieve relevant documents from the entire corpus instead of how to rerank a potentially biased sample of documents.
Neural Logic Reasoning
Both reasoning and generalization ability are important for prediction tasks such as recommender systems, where reasoning provides strong connection between user history and target items for accurate prediction, and generalization helps the model to draw a robust user portrait over noisy inputs.
RepBERT: Contextualized Text Embeddings for First-Stage Retrieval
Although exact term match between queries and documents is the dominant method to perform first-stage retrieval, we propose a different approach, called RepBERT, to represent documents and queries with fixed-length contextualized embeddings.
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.
