Dissociation of Faithful and Unfaithful Reasoning in LLMs

1 code implementation • 23 May 2024 • Evelyn Yee, Alice Li, Chenyu Tang, Yeon Ho Jung, Ramamohan Paturi, Leon Bergen

We identify factors that shift LLM recovery behavior: LLMs recover more frequently from obvious errors and in contexts that provide more evidence for the correct answer.

IR2: Information Regularization for Information Retrieval

1 code implementation • 25 Feb 2024 • Jianyou Wang, Kaicheng Wang, Xiaoyue Wang, Weili Cao, Ramamohan Paturi, Leon Bergen

This approach, representing a novel application of regularization techniques in synthetic data creation for IR, is tested on three recent IR tasks characterized by complex queries: DORIS-MAE, ArguAna, and WhatsThatBook.

Information Retrieval Retrieval +1

BIRCO: A Benchmark of Information Retrieval Tasks with Complex Objectives

1 code implementation • 21 Feb 2024 • Xiaoyue Wang, Jianyou Wang, Weili Cao, Kaicheng Wang, Ramamohan Paturi, Leon Bergen

We present the Benchmark of Information Retrieval (IR) tasks with Complex Objectives (BIRCO).

Information Retrieval Language Modelling +2

DORIS-MAE: Scientific Document Retrieval using Multi-level Aspect-based Queries

1 code implementation • 7 Oct 2023 • Jianyou Wang, Kaicheng Wang, Xiaoyue Wang, Prudhviraj Naidu, Leon Bergen, Ramamohan Paturi

In scientific research, the ability to effectively retrieve relevant documents based on complex, multifaceted queries is critical.

Retrieval