Thailand

It is very challenging to curate a dataset for language-specific knowledge and common sense in order to evaluate natural language understanding capabilities of language models. Due to the limitation in the availability of annotators, most current multilingual datasets are created through translation, which cannot evaluate such language-specific aspects. Therefore, we propose Multilingual CommonsenseQA (mCSQA) based on the construction process of CSQA but leveraging language models for a more efficient construction, e.g., by asking LM to generate questions/answers, refine answers and verify QAs followed by reduced human efforts for verification. Constructed dataset is a benchmark for cross-lingual language-transfer capabilities of multilingual LMs, and experimental results showed high language-transfer capabilities for questions that LMs could easily solve, but lower transfer capabilities for questions requiring deep knowledge or commonsense. This highlights the necessity of language-specific datasets for evaluation and training. Finally, our method demonstrated that multilingual LMs could create QA including language-specific knowledge, significantly reducing the dataset creation cost compared to manual creation. The datasets are available at https://huggingface.co/datasets/yusuke1997/mCSQA.

ACL 2024

mCSQA: Multilingual Commonsense Reasoning Dataset with Unified Creation Strategy by Language Models and Humans

human-ai interaction

dataset construction

commonsenseqa

culture

language model

commonsense

question answering

multilingual

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.

Memorisation is a natural part of learning from real-world data: neural models pick up on atypical input-output combinations and store those training examples in their parameter space. That this happens is well-known, but how and where are questions that remain largely unanswered. Given a multi-layered neural model, where does memorisation occur in the millions of parameters?
Related work reports conflicting findings: a dominant hypothesis based on image classification is that lower layers learn generalisable features and that deeper layers specialise and memorise. Work from NLP suggests this does not apply to language models, but has been mainly focused on memorisation of facts.
We expand the scope of the localisation question to 12 natural language classification tasks and apply 4 memorisation localisation techniques.
Our results indicate that memorisation is a gradual process rather than a localised one, establish that memorisation is task-dependent, and give nuance to the generalisation first, memorisation second hypothesis.

Generalisation First, Memorisation Second? Memorisation Localisation for Natural Language Classification Tasks

Despite outstanding performance in a variety of Natural Language Processing (NLP) tasks, recent studies have revealed that NLP models are vulnerable to adversarial attacks that slightly perturb the input to cause the models to misbehave. Several attacks can even compromise the model without requiring access to the model architecture or model parameters (i.e., a blackbox setting), and thus are detrimental to existing NLP applications. To perform these attacks, the adversary queries the victim model many times to determine the most important parts in an input text and transform. In this work, we propose a lightweight and attack-agnostic defense whose main goal is to perplex the process of generating an adversarial example in these query-based black-box attacks; that is to fool the textual fooler. This defense, named AdvFooler, works by randomizing the latent representation of the input at inference time. Different from existing defenses, AdvFooler does not necessitate additional computational overhead during training nor does it rely on assumptions about the potential adversarial perturbation set while having a negligible impact on the model’s accuracy. Our theoretical and empirical analyses highlight the significance of robustness resulting from confusing the adversary via randomizing the latent space, as well as the impact of randomization on clean accuracy. Finally, we empirically demonstrate near state-of-the-art robustness of AdvFooler against representative adversarial attacks on two benchmark datasets.

Fooling the Textual Fooler via Randomizing Latent Representations

Modern natural language processing (NLP) systems thrive when given access to large datasets. However, a large fraction of the world's languages are not privy to such benefits due to sparse documentation and inadequate digital representation. This is especially true for Indian regional languages. As a first step towards expanding the reach of NLP technologies to extremely low-resource Indian languages, we present a new parallel part-of-speech (POS) evaluation dataset for Angika, Magahi, Bhojpuri and Hindi. Angika, Magahi, Bhojpuri, along with the more well-known Hindi, are all languages spoken in the Indian states of Bihar, Jharkhand and West Bengal. Ours is notably the first NLP resource, even for a shallow NLP task like POS-tagging, for Angika. We establish POS-tagging baselines using state-of-the-art multilingual pretrained language models (PLMs) finetuned on Hindi data, and show zero-shot evaluations on the other three languages. While all four languages use the same Devanagari script, pretrained tokenizers underperform in zero-shot on the three languages. We propose a simple look-back fix to address the tokenization challenge yielding F1-score improvements of up to 8% on Angika and show how it comes very close to an oracle setting when the underlying Hindi word is known (and can be accurately tokenized).

Part-of-speech Tagging for Extremely Low-resource Indian Languages

This paper investigates unsupervised multimodal domain adaptation for multimodal emotion recognition, which is a solution for data scarcity yet remains under studied. Due to the varying distribution discrepancies of different modalities between source and target domains, the primary challenge lies in how to balance the domain alignment across modalities to guarantee they are all well aligned. To achieve this, we first develop our model based on the information bottleneck theory to learn optimal representation for each modality independently. Then, we align the domains via matching the label distributions and the representations. In order to balance the representation alignment, we propose to minimize a surrogate of the alignment losses, which is equivalent to adaptively adjusting the weights of the modalities throughout training, thus achieving balanced domain alignment across modalities. Overall, the proposed approach features \textbf{A}daptively \textbf{m}odality-bal\textbf{an}ced \textbf{d}omain \textbf{a}daptation, dubbed \textbf{Amanda}, for multimodal emotion recognition. Extensive empirical results on commonly used benchmark datasets demonstrate that Amanda significantly outperforms competing approaches. The code is available at \url{https://github.com/sunjunaimer/Amanda}.

Amanda: Adaptively Modality-Balanced Domain Adaptation for Multimodal Emotion Recognition

Deepfakes, particularly in the auditory domain, have become a significant threat, necessitating the development of robust countermeasures. This paper addresses the escalating challenges posed by deepfake attacks on Automatic Speaker Verification (ASV) systems. We present a novel Urdu deepfake audio dataset for deepfake detection, focusing on two spoofing attacks – Tacotron and VITS TTS. The dataset construction involves careful consideration of phonemic cover and balance and comparison with existing corpora like PRUS and PronouncUR. Evaluation with AASIST-L model shows EERs of 0.495 and 0.524 for VITS TTS and Tacotron-generated audios, respectively, with variability across speakers. Further, this research implements a detailed human evaluation, incorporating a user study to gauge whether people are able to discern deepfake audios from real (bonafide) audios. The ROC curve analysis shows an area under the curve (AUC) of 0.63, indicating that individuals demonstrate a limited ability to detect deepfakes (approximately 1 in 3 fake audio samples are regarded as real). Our work contributes a valuable resource for training deepfake detection models in low-resource languages like Urdu, addressing the critical gap in existing datasets. The dataset is publicly available at: https://github.com/CSALT-LUMS/urdu-deepfake-dataset.

Deepfake Defense: Constructing and Evaluating a Specialized Urdu Deepfake Audio Dataset

The remarkable multimodal capabilities demonstrated by OpenAI's GPT-4 have sparked significant interest in the development of multimodal Large Language Models (LLMs). A primary research objective of such models is to align visual and textual modalities effectively while comprehending human instructions.
Current methodologies often rely on annotations derived from benchmark datasets to construct image-dialogue datasets for training purposes, akin to instruction tuning in LLMs. However, these datasets often exhibit domain bias, potentially constraining the generative capabilities of the models. In an effort to mitigate these limitations, we propose a novel data collection methodology that synchronously synthesizes images and dialogues for visual instruction tuning. This approach harnesses the power of generative models, marrying the abilities of ChatGPT and text-to-image generative models to yield a diverse and controllable dataset with varied image content. This not only provides greater flexibility compared to existing methodologies but also significantly enhances several model capabilities. Our research includes comprehensive experiments conducted on various datasets using the open-source LLAVA model as a testbed for our proposed pipeline. Our results underscore marked enhancements across more than ten commonly assessed capabilities.

Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data

Large language models have achieved remarkable success in general language understanding tasks. However, as a family of generative methods with the objective of next token prediction, the semantic evolution with the depth of these models are not fully explored, unlike their predecessors, such as BERT-like architectures. In this paper, we specifically investigate the bottom-up evolution of lexical semantics for a popular LLM, namely Llama2, by probing its hidden states at the end of each layer using a contextualized word identification task. Our experiments show that the representations in lower layers encode lexical semantics, while the higher layers, with weaker semantic induction, are responsible for prediction. This is in contrast to models with discriminative objectives, such as mask language modeling, where the higher layers obtain better lexical semantics. The conclusion is further supported by the monotonic increase in performance via the hidden states for the last meaningless symbols, such as punctuation, in the prompting strategy. Our codes are available at https://github.com/RyanLiut/LLM_LexSem.

Fantastic Semantics and Where to Find Them: Investigating Which Layers of Generative LLMs Reflect Lexical Semantics

How can we construct an automated debate judge to evaluate an extensive, vibrant, multi-turn debate? 
This task is challenging, as judging a debate involves grappling with lengthy texts, intricate argument relationships, and multi-dimensional assessments.
At the same time, current research mainly focuses on short dialogues, rarely touching upon the evaluation of an entire debate.
In this paper, by leveraging Large Language Models (LLMs), we propose Debatrix, which makes the analysis and assessment of multi-turn debates more aligned with majority preferences. 
Specifically, Debatrix features a vertical, iterative chronological analysis and a horizontal, multi-dimensional evaluation collaboration.
To align with real-world debate scenarios, we introduced the PanelBench benchmark, comparing our system's performance to actual debate outcomes.
The findings indicate a notable enhancement over directly using LLMs for debate evaluation.
Source code and benchmark data are available at https://github.com/ljcleo/debatrix.

Debatrix: Multi-dimensional Debate Judge with Iterative Chronological Analysis Based on LLM

Recent work showed the possibility of building open-vocabulary large language models (LLMs) that directly operate on pixel representations. These models are implemented as autoencoders that reconstruct masked patches of rendered text.
However, these pixel-based LLMs are limited to discriminative tasks (e.g., classification) and, similar to BERT, cannot be used to generate text.

Therefore, they cannot be used for generative tasks such as free-form question answering. In this work, we introduce PIXAR, the first pixel-based autoregressive LLM that performs text generation. Consisting of only a decoder, PIXAR can perform free-form generative tasks while keeping the number of parameters on par with previous encoder-decoder models.

Furthermore, we highlight the challenges of generating text as non-noisy images and show this is due to using a maximum likelihood objective. To overcome this problem, we propose an adversarial pretraining stage that improves the readability and accuracy of PIXAR by 8.1 on LAMBADA and 8.5 on bAbI--- making it comparable to GPT-2 on text generation tasks.

This paves the way to build open-vocabulary LLMs that operate on perceptual input only and calls into question the necessity of the usual symbolic input representation, i.e., text as (sub)tokens.

PIXAR: Auto-Regressive Language Modeling in Pixel Space

Recent advances in Large Language Models (LLMs) have shown inspiring achievements in constructing autonomous agents that rely on
language descriptions as inputs. However, it remains unclear how well LLMs can function as few-shot or zero-shot embodied agents in dynamic interactive environments. To address this gap, we introduce LangSuit·E, a versatile and simulation-free testbed featuring 6 representative embodied tasks in textual embodied worlds. Compared with previous LLM-based testbeds, LangSuit·E (i) offers adaptability to diverse environments without multiple simulation engines, (ii) evaluates agents’ capacity to develop “internalized world knowledge” with embodied observations, and (iii) allows easy customization of communication and action strategies. To address the embodiment challenge, we devise a novel chain-of-thought (CoT) schema, EmMem, which summarizes embodied states w.r.t. history information. Comprehensive benchmark results illustrate challenges and insights of embodied planning. LangSuit·E represents a significant step toward building embodied generalists in the context of language models.

Premium content

mCSQA: Multilingual Commonsense Reasoning Dataset with Unified Creation Strategy by Language Models and Humans

Downloads

Next from ACL 2024

Generalisation First, Memorisation Second? Memorisation Localisation for Natural Language Classification Tasks

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES