paper-with-me

Papers

Characterizing Large Language Models as Rationalizers of Knowledge-intensive Tasks

2023-11-09 · Aditi Mishra, Sajjadur Rahman, Hannah Kim, Kushan Mitra, Estevam Hruschka

Large language models (LLMs) are proficient at generating fluent text with minimal task-specific supervision. Yet, their ability to provide well-grounded rationalizations for knowledge-intensive tasks remains under-explored. Such tasks, like commonsense multiple-choice questions, require rationales based on world knowledge to support predictions and refute alternate options. We consider the task of generating knowledge-guided rationalization in natural language by using expert-written examples in a few-shot manner. Surprisingly, crowd-workers preferred knowledge-grounded rationales over crowdsourced rationalizations, citing their factuality, sufficiency, and comprehensive refutations. Although LLMs-generated rationales were preferable, further improvements in conciseness and novelty are required. In another study, we show how rationalization of incorrect model predictions erodes humans' trust in LLM-generated rationales. Motivated by these observations, we create a two-stage pipeline to review task predictions and eliminate potential incorrect decisions before rationalization, enabling trustworthy rationale generation.

📄 PDF Abstract BibTeX arXiv:2311.05085

Code (0)

등록된 구현이 없습니다.

Tasks

Multiple-choiceWorld Knowledge

Similar Papers 제목 키워드 기반

Tailoring Self-Rationalizers with Multi-Reward Distillation

2023-11-06 · Sahana Ramnath, Brihi Joshi, Skyler Hallinan, Ximing Lu 외

Large language models (LMs) are capable of generating free-text rationales to aid question answering. However, prior work 1) suggests that useful self-rationalization is emergent only at significant scales (e.g., 175B pa…

DiversityQuestion AnsweringStrategyQA

A Survey of Knowledge-Intensive NLP with Pre-Trained Language Models

2022-02-17 · Da Yin, Li Dong, Hao Cheng, Xiaodong Liu 외

With the increasing of model capacity brought by pre-trained language models, there emerges boosting needs for more knowledgeable natural language processing (NLP) models with advanced functionalities including providing…

Language ModelingLanguage Modelling

Synergistic Multi-Agent Framework with Trajectory Learning for Knowledge-Intensive Tasks

2024-07-13 · Shengbin Yue, Siyuan Wang, Wei Chen, Xuanjing Huang 외

Recent advancements in Large Language Models (LLMs) have led to significant breakthroughs in various natural language processing tasks. However, generating factually consistent responses in knowledge-intensive scenarios …

HallucinationNavigate

Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Tasks

2023-05-28 · NeurIPS 2023 11 · Minki Kang, Seanie Lee, Jinheon Baek, Kenji Kawaguchi 외

Large Language Models (LLMs) have shown promising performance in knowledge-intensive reasoning tasks that require a compound understanding of knowledge. However, deployment of the LLMs in real-world applications can be c…

MedQAMemorizationStrategyQA

Generate rather than Retrieve: Large Language Models are Strong Context Generators

2022-09-21 · Wenhao Yu, Dan Iter, Shuohang Wang, Yichong Xu 외

Knowledge-intensive tasks, such as open-domain question answering (QA), require access to a large amount of world or domain knowledge. A common approach for knowledge-intensive tasks is to employ a retrieve-then-read pip…

Language ModelingLanguage ModellingLarge Language ModelOpen-Domain Question Answering