Search Results for author:
Found 14 papers, 10 papers with code
Ranked List Truncation for Large Language Model-based Re-Ranking
RLT is crucial for re-ranking as it can improve re-ranking efficiency by sending variable-length candidate lists to a re-ranker on a per-query basis.
Query Performance Prediction using Relevance Judgments Generated by Large Language Models
This allows us to predict any IR evaluation measure using the generated relevance judgments as pseudo-labels; Also, this allows us to interpret predicted IR evaluation measures, and identify, track and rectify errors in generated relevance judgments to improve QPP quality.
CAUSE: Counterfactual Assessment of User Satisfaction Estimation in Task-Oriented Dialogue Systems
In this work, we leverage large language models (LLMs) and unlock their ability to generate satisfaction-aware counterfactual dialogues to augment the set of original dialogues of a test collection.
Measuring Bias in a Ranked List using Term-based Representations
With TExFAIR, we extend the AWRF framework to allow for the evaluation of fairness in settings with term-based representations of groups in documents in a ranked list.
Self-seeding and Multi-intent Self-instructing LLMs for Generating Intent-aware Information-Seeking dialogs
Furthermore, we propose SOLID-RL, which is further trained to generate a dialog in one step on the data generated by SOLID.
Answer Retrieval in Legal Community Question Answering
Furthermore, we propose LegalQA: a real-world benchmark dataset for evaluating answer retrieval in the legal domain.
Enhancing Documents with Multidimensional Relevance Statements in Cross-encoder Re-ranking
In this paper, we propose a novel approach to consider multiple dimensions of relevance beyond topicality in cross-encoder re-ranking.
Generating Synthetic Documents for Cross-Encoder Re-Rankers: A Comparative Study of ChatGPT and Human Experts
We introduce a new dataset, ChatGPT-RetrievalQA, and compare the effectiveness of models fine-tuned on LLM-generated and human-generated data.
Retrieval for Extremely Long Queries and Documents with RPRS: a Highly Efficient and Effective Transformer-based Re-Ranker
Furthermore, our method solves the problem of the low-resource training in QBD retrieval tasks as it does not need large amounts of training data, and has only three parameters with a limited range that can be optimized with a grid search even if a small amount of labeled data is available.
Injecting the BM25 Score as Text Improves BERT-Based Re-rankers
In this paper we propose a novel approach for combining first-stage lexical retrieval models and Transformer-based re-rankers: we inject the relevance score of the lexical model as a token in the middle of the input of the cross-encoder re-ranker.
On the Interpolation of Contextualized Term-based Ranking with BM25 for Query-by-Example Retrieval
In this work, we examine the generalizability of two of these deep contextualized term-based models in the context of query-by-example (QBE) retrieval in which a seed document acts as the query to find relevant documents.
LeiBi@COLIEE 2022: Aggregating Tuned Lexical Models with a Cluster-driven BERT-based Model for Case Law Retrieval
Our methodology consists of four steps; in detail, given a legal case as a query, we reformulate it by extracting various meaningful sentences or n-grams.
Expert Finding in Legal Community Question Answering
In the legal domain, there is a large knowledge gap between the experts and the searchers, and the content on the legal QA websites consist of a combination formal and informal communication.
DoSSIER@COLIEE 2021: Leveraging dense retrieval and summarization-based re-ranking for case law retrieval
We address this challenge by combining lexical and dense retrieval methods on the paragraph-level of the cases for the first stage retrieval.
