Thailand

Social biases in LLMs are usually measured via bias benchmark datasets. Current benchmarks have limitations in scope, grounding, quality, and human effort required. Previous work has shown success with a community-sourced, rather than crowd-sourced, approach to benchmark development. However, this work still required considerable effort from annotators with relevant lived experience. This paper explores whether an LLM (specifically, GPT-3.5-Turbo) can assist with the task of developing a bias benchmark dataset from responses to an open-ended community survey. We also extend the previous work to a new community and set of biases: the Jewish community and antisemitism. Our analysis shows that GPT-3.5-Turbo has poor performance on this annotation task and produces unacceptable quality issues in its output. Thus, we conclude that GPT-3.5-Turbo is not an appropriate substitute for human annotation in sensitive tasks related to social biases, and that its use actually negates many of the benefits of community-sourcing bias benchmarks.

ACL 2024

GPT is Not an Annotator: The Necessity of Human Annotation in Fairness Benchmark Construction

llm evaluation

safety

ethics

fairness

bias

poster

### Welcome!
The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) will take place in Bangkok, Thailand from August 11th to 16th, 2024. Our Virtual Poster Sessions will take place online Thursday, August 22, 2024.

You are required to register for this event. **Please register [here](https://2024.aclweb.org/registration). **

If you have already registered, please check your inbox for an email from Underline granting you access to ACL 2024 content.

Please register!

The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) will take place in Bangkok, Thailand from August 11th to 16th, 2024. More information will be announced soon.

We propose RESTA to perform LLM realignment towards safety, which gets compromised due to downstream task fine-tuning. RESTA stands for REstoring Safety through Task Arithmetic. At its core, it involves a simple arithmetic addition of a safety vector to the weights of the compromised model. We demonstrate the effectiveness of RESTA in both parameter-efficient and full fine-tuning, covering a wide range of downstream tasks, including instruction following in Chinese, English, and Hindi, as well as problem-solving capabilities in Code and Math. We also showcase the generalizability of RESTA on three existing safety evaluation benchmarks and a multilingual benchmark dataset proposed as a part of this work, consisting of 550 harmful questions covering 11 categories, each with 5 sub-categories of harm. Overall, RESTA decreases the harmfulness of the compromised model from 18.6% to 5.1% and from 9.2% to 1.5% in parameter-efficient and full fine-tuning, respectively, while maintaining most of the model's performance on the task. We release the source codes at: https://github.com/declare-lab/resta.

Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic

Standard natural language processing (NLP) pipelines operate on symbolic representations of language, which typically consist of sequences of discrete tokens. However, creating an analogous representation for ancient logographic writing systems is an extremely labor-intensive process that requires expert knowledge. At present, a large portion of logographic data persists in a purely visual form due to the absence of transcription—this issue poses a bottleneck for researchers seeking to apply NLP toolkits to study ancient logographic languages: most of the relevant data are images of writing. 
This paper investigates whether direct processing of visual representations of language offers a potential solution. We introduce LogogramNLP, the first benchmark enabling NLP analysis of ancient logographic languages, featuring both transcribed and visual datasets
for four writing systems along with annotations for tasks like classification, translation, and parsing. Our experiments compare systems that
employ recent visual and text encoding strategies as backbones. The results demonstrate that visual representations outperform textual representations for some investigated tasks, suggesting that visual processing pipelines may unlock a large amount of cultural heritage data of logographic languages for NLP-based analyses. Data and code are available at https: //logogramNLP.github.io/.

LogogramNLP: Comparing Visual and Textual Representations of Ancient Logographic Writing Systems for NLP

This paper presents a systematic defense of large language model (LLM) hallucinations or `confabulations' as a potential resource instead of a categorically negative pitfall. The standard view is that confabulations are inherently problematic and AI research should eliminate this flaw. In this paper, we argue and empirically demonstrate that measurable semantic characteristics of LLM confabulations mirror a human propensity to utilize increased narrativity as a cognitive resource for sense-making and communication. In other words, it has potential value. Specifically, we analyze popular hallucination benchmarks and reveal that hallucinated outputs display increased levels of narrativity and semantic coherence relative to veridical outputs. This finding reveals a tension in our usually dismissive understandings of confabulation. It suggests, counter-intuitively, that the tendency for LLMs to confabulate may be intimately associated with a positive capacity for coherent narrative-text generation.

Confabulation: The Surprising Value of Large Language Model Hallucinations

Structured Natural Language Processing (XNLP) is an important subset of NLP that entails understanding the underlying semantic or syntactic structure of texts, which serves as a foundational component for many downstream applications. Despite certain recent efforts to explore universal solutions for specific categories of XNLP tasks, a comprehensive and effective approach for unifying all XNLP tasks long remains underdeveloped. Meanwhile, while XNLP demonstration systems are vital for researchers exploring various XNLP tasks, existing platforms can be limited to, e.g., supporting few XNLP tasks, lacking interactivity and universalness. To this end, we propose an advanced XNLP demonstration system, where we leverage LLM to achieve universal XNLP, with one model for all with high generalizability. Overall, our system advances in multiple aspects, including universal XNLP modeling, high performance, interpretability, scalability, and interactivity, offering a unified platform for exploring diverse XNLP tasks in the community.

XNLP: An Interactive Demonstration System for Universal Structured NLP

Evaluation is pivotal for honing Large Language Models (LLMs), pinpointing their capabilities and guiding enhancements. The rapid development of LLMs calls for a lightweight and easy-to-use framework for swift evaluation deployment. However, due to the various implementation details to consider, developing a comprehensive evaluation platform is never easy. Existing platforms are often complex and poorly modularized, hindering seamless incorporation into researcher's workflows. This paper introduces UltraEval, a user-friendly evaluation framework characterized by lightweight, comprehensiveness, modularity, and efficiency. We identify and reimplement three core components of model evaluation (models, data, and metrics). The resulting composability allows for the free combination of different models, tasks, prompts, and metrics within a unified evaluation workflow. Additionally, UltraEval supports diverse models owing to a unified HTTP service and provides sufficient inference acceleration.

UltraEval: A Lightweight Platform for Flexible and Comprehensive Evaluation for LLMs

Digital documents, such as PDFs, are vital in business workflows, enabling communication, documentation, and collaboration. Handling PDFs can involve navigating complex workflows and numerous tools (e.g., comprehension, annotation, editing), which can be tedious and time-consuming for users. We introduce DocPilot, an AI-assisted document workflow Copilot system capable of understanding user intent and executing tasks accordingly to help users streamline their workflows. DocPilot undertakes intelligent orchestration of various tools through LLM prompting in four steps: (1) Task plan generation, (2) Task plan verification and self-correction, (3) Multi-turn User Feedback, and (4) Task Plan Execution via Code Generation and Error log-based Code Self-Revision. The primary goal of this system is to free the user from the intricacies of document editing, enabling them to focus on the creative aspects and enrich their document management experience.

DocPilot: Copilot for Automating PDF Edit Workflows in Documents

The proliferation of fake news poses a significant threat not only by disseminating misleading information but also by undermining the very foundations of democracy. 
The recent advance of generative artificial intelligence has further exacerbated the challenge of distinguishing genuine news from fabricated stories. 
In response to this challenge, we introduce VeraCT Scan, a novel retrieval-augmented system for fake news detection. This system operates by extracting the core facts from a given piece of news and subsequently conducting an internet-wide search to identify corroborating or conflicting reports. Then sources' credibility is leveraged for information verification. 
Besides determining the veracity of news, we also provide transparent evidence and reasoning to support its conclusions, resulting in the interpretability and trust in the results. In addition to GPT-4 Turbo, Llama-2 13B is also fine-tuned for news content understanding, information verification, and reasoning. Both implementations have demonstrated state-of-the-art accuracy in the realm of fake news detection.

VeraCT Scan: Retrieval-Augmented Fake News Detection with Justifiable Reasoning

We describe PyFoma, an open-source Python module for constructing weighted and unweighted finite-state transducers and automata from regular expressions, string rewriting rules, right-linear grammars, or low-level state/transition manipulation. A large variety of standard algorithms for working with finite-state machines is included, with a particular focus on the needs of linguistic and NLP applications. The data structures and code in the module are designed for legibility to allow for potential use in teaching the theory and algorithms associated with finite-state machines.

PyFoma: a Python finite-state compiler module

We present a synthetic data approach for instruction-tuning large language models (LLMs) for low-resource languages in a data-efficient manner, specifically focusing on Thai. We identify three key properties that contribute to the effectiveness of instruction-tuning datasets: fluency, diversity, and cultural context. We propose a seed-data-free framework for generating synthetic instruction-tuning data that incorporates these essential properties. Our framework employs an LLM to generate diverse topics, retrieve relevant contexts from Wikipedia, and create instructions for various tasks, such as question answering, summarization, and conversation. The experimental results show that our best-performing synthetic dataset, which incorporates all three key properties, achieves competitive performance using only 5,000 instructions when compared to state-of-the-art Thai LLMs trained on hundreds of thousands of instructions.

Seed-Free Synthetic Data Generation Framework for Instruction-Tuning LLMs: A Case Study in Thai

Identifying beneficial tasks to transfer from is a crucial step toward successful transfer learning in the paradigm of intermediate-task transfer learning. In this work, we experiment on 130 source-target task combinations and demonstrate that the transfer performance exhibits severe variance across different source tasks and training seeds, highlighting the crucial role of intermediate-task selection in a broader context. We compare four representative task selection methods in a unified setup, focusing on their effectiveness and consistency. Compared to embedding-free methods and text embeddings, task embeddings constructed from fine-tuned weights can better estimate task transferability by improving task prediction accuracy from 2.59\% to 3.96\%. Despite its strong performance, we observe that the task embeddings do not consistently demonstrate superiority for tasks requiring reasoning abilities. Furthermore, we introduce a novel method that measures pairwise token similarity using maximum inner product search, leading to the highest performance in task-transfer prediction. Our findings suggest that token-wise similarity is better predictive for predicting transferability compared to averaging weights.

Downloads

Next from ACL 2024

Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES