Singapore

Detecting hallucinations in natural language processing (NLP) is a critical undertaking that demands a deep understanding of both the semantic and pragmatic aspects of languages. Cognitive approaches that leverage users’ behavioural signals, such as gaze, have demonstrated effectiveness in addressing NLP tasks with similar linguistic complexities. However, their potential in the context of hallucination detection remains largely unexplored. In this paper, we propose a novel cognitive approach for hallucination detection that leverages gaze signals from humans. We first collect and introduce an eye tracking corpus (IITB-HGC: IITB-Hallucination Gaze corpus) consisting of 500 instances, annotated by five annotators for hallucination detection. Our analysis reveals that humans selectively attend to relevant parts of the text based on distributional similarity, similar to the attention bias phenomenon in psychology. We identify two attention strategies employed by humans: global attention, which focuses on the most informative sentence, and local attention, which focuses on important words within a sentence. Leveraging these insights, we propose a novel cognitive framework for hallucination detection that incorporates these attention biases. Experimental evaluations on the FactCC dataset demonstrate the efficacy of our approach, obtaining a balanced accuracy of 87.1%. Our study highlights the potential of gaze-based approaches in addressing the task of hallucination detection and sheds light on the cognitive processes employed by humans in identifying inconsistencies.

EMNLP 2023

Eyes Show the Way: Modelling Gaze Behaviour for Hallucination Detection

behavioural analysis

hallucination

gaze

cognition

eye-tracking

**Welcome to EMNLP 2023!**

On behalf of the EMNLP 2023 Organizing Committee, I extend a warm and heartfelt welcome to all of you to the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP). It is with immense pleasure and excitement that we gather here in Singapore, a vibrant hub of innovation and technological advancement.

The conference program is packed with insightful presentations, thought-provoking workshops, and engaging networking opportunities. In addition to the technical sessions, we have also planned several social events that will provide you with the opportunity to connect with your colleagues.

The conference is held in person at the Resorts World Convention Centre in Singapore, and available on-line with the help of Underline.

For those in Singapore, I hope that you will find time to explore the exciting Sentosa Island, Gardens by the Bay, Singapore Botanic Gardens and the many other attractions unique to Singapore.

Of course, we are grateful to our sponsors and partners for their generous support of EMNLP 2023, whose contributions make it possible for us to host this world-class event.

Yuji Matsumoto (RIKEN AIP) 
EMNLP 2023 General Chair

To access the **EMNLP 2023** event page on Underline, you need to register for the Conference. 
Please follow **[this link](https://2023.emnlp.org/registration/)** for more details.

EMNLP 2023 took place in Singapore from Dec 6th to Dec 10th, 2023.

poster

The probing classiﬁers framework has been employed for interpreting deep neural network models for a variety of natural language processing (NLP) applications. Studies, however, have largely focused on sentencelevel NLP tasks. This work is the ﬁrst to apply the probing paradigm to representations learned for document-level information extraction (IE). We designed eight embedding probes to analyze surface, semantic, and event-understanding capabilities relevant to document-level event extraction. We apply them to the representations acquired by learning models from three different LLM-based document-level IE approaches on a standard dataset. We found that trained encoders from these models yield embeddings that can modestly improve argument detections and labeling but only slightly enhance event-level tasks, albeit trade-offs in information helpful for coherence and event-type prediction. We further found that encoder models struggle with document length and cross-sentence discourse.

Probing Representations for Document-level Event Extraction

Document-level neural machine translation (DNMT) has shown promising results by incorporating context information through increased maximum lengths of source and target sentences. However, this approach also introduces a length bias problem, whereby DNMT suffers from significant translation quality degradation when decoding sentences that are much shorter or longer than the maximum sentence length during training, i.e., the length bias problem. To prevent the model from neglecting shorter sentences, we sample the training data to ensure a more uniform distribution across different sentence lengths while progressively increasing the maximum sentence length during training. Additionally, we introduce a length-normalized attention mechanism to aid the model in focusing on target information, mitigating the issue of attention divergence when processing longer sentences. Furthermore, during the decoding stage of DNMT, we propose a sliding decoding strategy that limits the length of target sentences to not exceed the maximum length encountered during training. The experimental results indicate that our method can achieve state-of-the-art results on several open datasets, and further analysis shows that our method can significantly alleviate the length bias problem.

Addressing the Length Bias Challenge in Document-Level Neural Machine Translation

Recent works in open-domain question answering (QA) have explored generating context passages from large language models (LLMs), replacing the traditional retrieval step in the QA pipeline. However, it is not well understood why generated passages can be more effective than retrieved ones. This study revisits the conventional formulation of QA and introduces the concept of $\textit{knowledge corpus error}$. This error arises when the knowledge corpus used for retrieval is only a subset of the entire string space, potentially excluding more helpful passages that exist outside the corpus. LLMs may mitigate this shortcoming by generating passages in a larger space. We come up with an experiment of paraphrasing human-annotated gold context using LLMs to observe knowledge corpus error empirically. Our results across three QA benchmarks reveal an increased performance (10\% - 13\%) when using paraphrased passage, indicating a signal for the existence of knowledge corpus error.

Knowledge Corpus Error in Question Answering

Evaluation of dialogue systems requires assessing various aspects, among which appropriateness holds significance as a core element of communicative language competence. However, current evaluations heavily rely on human judgments, which are time-consuming, labor-intensive, prone to biases, and lacking objectivity. In this paper, we introduce Dialogue Act Appropriateness (DAA), a novel method that utilizes the underlying patterns of dialogue act transitions to evaluate the appropriateness of chatbot responses. We learn transition patterns from human-human dialogue corpora, evaluating chatbot appropriateness by measuring the similarity of their transition patterns to those observed in human-human dialogues. To validate DAA, we annotate a test dataset by manually evaluating the appropriateness of dialogues from multiple chatbot systems. The experimental results demonstrate a strong correlation between our evaluation metric and human ratings, establishing the reliability of DAA as a measure of dialogue appropriateness.

Automatic Evaluate Dialogue Appropriateness by Using Dialogue Act

Generated texts from large language models (LLMs) are remarkably close to high-quality human-authored text, raising concerns about their potential misuse in spreading false information and academic misconduct. Consequently, there is an urgent need for a highly practical detection tool capable of accurately identifying the source of a given text.
However, existing detection tools typically rely on access to LLMs and can only differentiate between machine-generated and human-authored text, failing to meet the requirements of fine-grained tracing, intermediary judgment, and rapid detection. Therefore, we propose LLMDet, a model-specific, secure, efficient, and extendable detection tool, that can source text from specific LLMs, such as GPT-2, OPT, LLaMA, and others. In LLMDet, we record the next-token probabilities of salient n-grams as features to calculate proxy perplexity for each LLM. By jointly analyzing the proxy perplexities of LLMs, we can determine the source of the generated text. Experimental results show that LLMDet yields impressive detection performance while ensuring speed and security, achieving 98.54\% precision and about $\times 5.0$ faster for recognizing human-authored text. Additionally, LLMDet can effortlessly extend its detection capabilities to a new open-source model. We will provide an open-source tool at \url{https://github.com/TrustedLLM/LLMDet}.

LLMDet: A Third Party Large Language Models Generated Text Detection Tool

Scaling pre-trained language models has resulted in large performance gains in various natural language processing tasks but comes with a large cost in memory requirements. Inspired by the position embeddings in transformers, we aim to simplify and reduce the memory footprint of the multi-head attention (MHA) mechanism. We propose an alternative module that uses only a single shared projection matrix and multiple head embeddings (MHE), i.e. one per head. We empirically demonstrate that our MHE attention is substantially more memory efficient compared to alternative attention mechanisms while achieving high predictive performance retention ratio to vanilla MHA on several downstream tasks. MHE attention only requires a negligible fraction of additional parameters ($3nd$, where $n$ is the number of attention heads and $d$ the size of the head embeddings) compared to a single-head attention, while MHA requires $(3n^2-3n)d^2-3nd$ additional parameters.

Pit One Against Many: Leveraging Attention-head Embeddings for Parameter-efficient Multi-head Attention

Large language models (LLMs) are a promising avenue for machine translation (MT). However, current LLM-based MT systems are brittle: their effectiveness highly depends on the choice of few-shot examples and they often require extra post-processing due to overgeneration. Alternatives such as finetuning on translation instructions are computationally expensive and may weaken in-context learning capabilities, due to overspecialization. In this paper, we provide a closer look at this problem. We start by showing that adapter-based finetuning with LoRA matches the performance of traditional finetuning while reducing the number of training parameters by a factor of 50. This method also outperforms few-shot prompting and eliminates the need for post-processing or in-context examples. However, we show that finetuning generally degrades few-shot performance, hindering adaptation capabilities. Finally, to obtain the best of both worlds, we propose a simple approach that incorporates few-shot examples during finetuning. Experiments on 10 language pairs show that our proposed approach recovers the original few-shot capabilities while keeping the added benefits of finetuning.

Steering Large Language Models for Machine Translation with Finetuning and In-Context Learning

In this work, we study the language model backbone replacement problem for personalized downstream tasks in a non-stationary on-device scenario. In real world, company may periodically update the knowledge and architectures of backbones to keep the competitive in the market, meanwhile, to accommodate the users' own preference, models are personalized to fit users' own distribution locally. Traditional full model tuning or transfer learning for such replacements often incur considerable local device training costs and necessitate extensive backpropagation within deep transformer layers. Addressing this issue, we propose a novel, lightweight tuning method for personalized NLP classification tasks post-backbone replacement. Our approach leverages a personalized matrix calculated from documents corresponding to users' old and new backbones. This matrix facilitates top-layer parameter tuning, drastically reducing backpropagation computation. To further mitigate training costs associated with matrix linear optimization, we employ correlation clustering to curate a few examples from personalized cluster sets for individuals. Our method achieves over 1000 times computation reduction in Flops for backpropagation and brings the user-specific initialization for personal matrix yielding significant performance boost compared with popular transfer learning methods.

FaLA: Fast Linear Adaptation for Replacing Backbone Models on Edge Devices

Emotion-Cause analysis has attracted the attention of researchers in recent years. However, most existing datasets are limited in size and number of emotion categories. They often focus on extracting parts of the document that contain the emotion cause and fail to provide more abstractive, generalizable root cause.
To bridge this gap, we introduce a large-scale dataset of emotion causes, derived from 9.8 million cleaned tweets over 15 years.
We describe our curation process, which includes a comprehensive pipeline for data gathering, cleaning, labeling, and validation, ensuring the dataset's reliability and richness. We extract emotion labels and provide abstractive summarization of the events causing emotions. 
The final dataset comprises over 700,000 tweets with corresponding emotion-cause pairs spanning 48 emotion classes, validated by human evaluators. 
The novelty of our dataset stems from its broad spectrum of emotion classes and the abstractive emotion cause that facilitates the development of an emotion-cause knowledge graph for nuanced reasoning.
Our dataset will enable the design of emotion-aware systems that account for the diverse emotional responses of different people for the same event.

EMO-KNOW: A Large Scale Dataset on Emotion-Cause

In-context learning (ICL) in Large Language Models (LLMs) has emerged as a powerful new learning paradigm. However, its underlying mechanism is still not well understood.
In particular, it is challenging to map it to the "standard" machine learning framework, where one uses a training set $S$ to find a best-fitting function $f(x)$ in some hypothesis class. Here we make progress on this problem by showing that the functions learned by ICL often have a very simple structure: they correspond to the transformer LLM whose only inputs are the query $x$ and a single "task vector" calculated from the training set. Thus, ICL can be seen as compressing $S$ into a single task vector $\boldsymbol{\theta}(S)$ and then using this task vector to modulate the transformer to produce the output.
We support the above claim via comprehensive experiments across a range of models and tasks.

Downloads

Next from EMNLP 2023

Probing Representations for Document-level Event Extraction

Similar lecture

Eyes Show the Way: Modelling Gaze Behaviour for Hallucination Detection

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from EMNLP 2023

Probing Representations for Document-level Event Extraction

Similar lecture

Eyes Show the Way: Modelling Gaze Behaviour for Hallucination Detection

Downloads