Towards Knowledgeable Language Models
@ ACL 2024 Workshop
August 12–17, 2024 hybrid in Bangkok, Thailand & remote
Knowledge has been an important pre-requisite for a variety of NLP applications, and is typically sourced from either structured knowledge sources such as knowledge bases and dictionaries or unstructured knowledge sources such as Wikipedia documents.
More recently, researchers have discovered that language models already possess a significant amount of knowledge through pre-training: LLMs can be used to generate commonsense knowledge and factual knowledge context for question answering. While the results are encouraging, there are still lingering questions:
This workshop examines the lifecycle of knowledge within language models:
Knowledge has been an important prerequisite for various NLP applications and is typically derived from either structured knowledge sources such as knowledge bases and dictionaries or unstructured knowledge sources such as Wikipedia documents and news articles.
It is known that language models already possess a significant amount of knowledge through pre-training: LLMs can be used to generate commonsense knowledge and factual knowledge when prompted to do so. However, beyond the surface, there are still many lingering questions such as “where the knowledge comes from”, “how do we quantify the amount of knowledge”, “is the knowledge reliable (and do LMs themselves know)”, “how can we augment LMs with domain-specific knowledge”, “how can we revise knowledge without hurting the reasoning abilities of LMs” and “how can we leverage knowledge to assist the self-correction of LMs”.
In this workshop, we want to bring together researchers who focus on different stages and different aspects (structured knowledge, unstructured knowledge, and knowledge acquired from LMs themselves) of the knowledge lifecycle to discuss the role of knowledge in the era of large language models.
Submission Topics
We welcome long (8 page) and short (4 page) paper submissions on all topics related to knowledgable LMs, including:
Analysis of knowledge within LMs: how much they know and where that knowledge is from. Enhancing LMs with existing knowledge sources (knowledge graphs, domain-specific databases, manuals, and rules, etc, either during training or inference). Analyzing and improving RAG (retrieval-augmented generation) systems Updating and editing knowledge in LMs. Knowledge extraction and generation using LMs Evaluation of knowledge utilization (faithfulness, truthfulness) by LMs. Identification and mitigation of LM hallucinations, factual error correction
We will also announce a Best Paper Award at our workshop sponsored by Amazon.
Submission Instructions
We welcome two types of papers: regular workshop papers and non-archival submissions. Only regular workshop papers will be included in the workshop proceedings. All submissions should be in PDF format following the ACL template and made through OpenReview submission portal (https://openreview.net/group?id=aclweb.org/ACL/2024/Workshop/KnowledgeLM)
All deadlines are 11:59 pm UTC-12h (“Anywhere on Earth”).
Submission Deadline | May 24 2024 |
---|---|
Decision Notifications | June 22 2024 |
Camera-Ready Deadline | July 6 2024 |
Workshop Date | 16 August 2024 |
Time | Program |
---|---|
9:00-9:10 | Opening remarks |
9:10-10:40 | Three keynote speeches (30 min each) |
10:40-11:30 | Panel discussion |
11:30-12:30 | Poster session |
12:30-13:30 | Student mentoring lunch session (pair senior researchers with junior researchers) |
13:30-15:00 | Three keynote speeches (30 min each) |
15:00-15:50 | Panel discussion |
15:50-16:50 | Oral paper session (12 min talk + 3 min QA) |
16:50-17:20 | Challenge track spotlight session (6 min talk) |
17:20-17:30 | Closing remarks |