We show that LLMs hallucinate because their output is not constrained to be synonymous with claims for which they have evidence: a condition that we call evidential closure. Information about the truth or falsity of sentences is not statistically identified in the standard neural probabilistic language model setup, and so cannot be conditioned on to generate new strings. We then show how to constrain LLMs to produce output that does satisfy evidential closure. A multimodal LLM must learn about the external world (perceptual learning); it must learn a mapping from strings to states of the world (extensional learning); and, to achieve fluency when generalizing beyond a body of evidence, it must learn mappings from strings to their synonyms (intensional learning). The output of a unimodal LLM must be synonymous with strings in a validated evidence set. Finally, we present a heuristic procedure, Learn-Babble-Prune, that yields faithful output from an LLM by rejecting output that is not synonymous with claims for which the LLM has evidence.
The paper investigates using a Large Language Model (LLM) to automatically perform web software tasks using click, scroll, and text input operations. Previous approaches, such as reinforcement learning (RL) or imitation learning, are inefficient to train and task-specific. Our method uses filtered Document Object Model (DOM) elements as observations and performs tasks step-by-step, sequentially generating small programs based on the current observations. We use in-context learning, either benefiting from a single manually provided example, or an automatically generated example based on a successful zero-shot trial. We evaluate the proposed method on the MiniWob++ benchmark. With only one in-context example, our WebWISE method achieves similar or better performance than other methods that require many demonstrations or trials.
Traditional pruning methods are known to be challenging to work in Large Language Models (LLMs) for Generative AI because of their unaffordable training process and large computational demands. For the first time, we introduce the information entropy of hidden state features into a pruning metric design, namely E-Sparse, to improve the accuracy of N:M sparsity on LLM. E-Sparse employs the information richness to leverage the channel importance, and further incorporates several novel techniques to put it into effect: (1) it introduces information entropy to enhance the significance of parameter weights and input feature norms as a novel pruning metric, and performs N:M sparsity without modifying the remaining weights. (2) it designs global naive shuffle and local block shuffle to quickly optimize the information distribution and adequately cope with the impact of N:M sparsity on LLMs' accuracy. E-Sparse is implemented as a Sparse-GEMM on FasterTransformer and runs on NVIDIA Ampere GPUs. Extensive experiments on the LLaMA family and OPT models show that E-Sparse can significantly speed up the model inference over the dense model (up to 1.53X) and obtain significant memory saving (up to 43.52%), with acceptable accuracy loss.
Humans subconsciously engage in geospatial reasoning when reading articles. We recognize place names and their spatial relations in text and mentally associate them with their physical locations on Earth. Although pretrained language models can mimic this cognitive process using linguistic context, they do not utilize valuable geospatial information in large, widely available geographical databases, e.g., OpenStreetMap. This paper introduces GeoLM, a geospatially grounded language model that enhances the understanding of geo-entities in natural language. GeoLM leverages geo-entity mentions as anchors to connect linguistic information in text corpora with geospatial information extracted from geographical databases. GeoLM connects the two types of context through contrastive learning and masked language modeling. It also incorporates a spatial coordinate embedding mechanism to encode distance and direction relations to capture geospatial context. In the experiment, we demonstrate that GeoLM exhibits promising capabilities in supporting toponym recognition, toponym linking, relation extraction, and geo-entity typing, which bridge the gap between natural language processing and geospatial sciences. The code is publicly available at https://github.com/knowledge-computing/geolm.
Security classifiers, designed to detect malicious content in computer systems and communications, can underperform when provided with insufficient training data. In the security domain, it is often easy to find samples of the negative (benign) class, and challenging to find enough samples of the positive (malicious) class to train an effective classifier. This study evaluates the application of natural language text generators to fill this data gap in multiple security-related text classification tasks. We describe a variety of previously-unexamined language-model fine-tuning approaches for this purpose and consider in particular the impact of disproportionate class-imbalances in the training set. Across our evaluation using three state-of-the-art classifiers designed for offensive language detection, review fraud detection, and SMS spam detection, we find that models trained with GPT-3 data augmentation strategies outperform both models trained without augmentation and models trained using basic data augmentation strategies already in common usage. In particular, we find substantial benefits for GPT-3 data augmentation strategies in situations with severe limitations on known positive-class samples.
Numerous debiasing techniques have been proposed to mitigate the gender bias that is prevalent in pretrained language models. These are often evaluated on datasets that check the extent to which the model is gender-neutral in its predictions. Importantly, this evaluation protocol overlooks the possible adverse impact of bias mitigation on useful gender knowledge. To fill this gap, we propose DiFair, a manually curated dataset based on masked language modeling objectives. DiFair allows us to introduce a unified metric, gender invariance score, that not only quantifies a model's biased behavior, but also checks if useful gender knowledge is preserved. We use DiFair as a benchmark for a number of widely-used pretained language models and debiasing techniques. Experimental results corroborate previous findings on the existing gender biases, while also demonstrating that although debiasing techniques ameliorate the issue of gender bias, this improvement usually comes at the price of lowering useful gender knowledge of the model.
The purpose of sequential recommendation is to utilize the interaction history of a user and predict the next item that the user is most likely to interact with. While data sparsity and cold start are two challenges that most recommender systems are still facing, many efforts are devoted to utilizing data from other domains, called cross-domain methods. However, general cross-domain methods explore the relationship between two domains by designing complex model architecture, making it difficult to scale to multiple domains and utilize more data. Moreover, existing recommendation systems use IDs to represent item, which carry less transferable signals in cross-domain scenarios, and user cross-domain behaviors are also sparse, making it challenging to learn item relationship from different domains. These problems hinder the application of multi-domain methods to sequential recommendation. Recently, large language models (LLMs) exhibit outstanding performance in world knowledge learning from text corpora and general-purpose question answering. Inspired by these successes, we propose a simple but effective framework for domain-agnostic recommendation by exploiting the pre-trained LLMs (namely LLM-Rec). We mix the user's behavior across different domains, and then concatenate the title information of these items into a sentence and model the user's behaviors with a pre-trained language model. We expect that by mixing the user's behaviors across different domains, we can exploit the common knowledge encoded in the pre-trained language model to alleviate the problems of data sparsity and cold start problems. Furthermore, we are curious about whether the latest technical advances in nature language processing (NLP) can transfer to the recommendation scenarios.
Red-teaming has been a widely adopted way to evaluate the harmfulness of Large Language Models (LLMs). It aims to jailbreak a model's safety behavior to make it act as a helpful agent disregarding the harmfulness of the query. Existing methods are primarily based on input text-based red-teaming such as adversarial prompts, low-resource prompts, or contextualized prompts to condition the model in a way to bypass its safe behavior. Bypassing the guardrails uncovers hidden harmful information and biases in the model that are left untreated or newly introduced by its safety training. However, prompt-based attacks fail to provide such a diagnosis owing to their low attack success rate, and applicability to specific models. In this paper, we present a new perspective on LLM safety research i.e., parametric red-teaming through Unalignment. It simply (instruction) tunes the model parameters to break model guardrails that are not deeply rooted in the model's behavior. Unalignment using as few as 100 examples can significantly bypass commonly referred to as CHATGPT, to the point where it responds with an 88% success rate to harmful queries on two safety benchmark datasets. On open-source models such as VICUNA-7B and LLAMA-2-CHAT 7B AND 13B, it shows an attack success rate of more than 91%. On bias evaluations, Unalignment exposes inherent biases in safety-aligned models such as CHATGPT and LLAMA- 2-CHAT where the model's responses are strongly biased and opinionated 64% of the time.
Even with the latest developments in deep learning and large-scale language modeling, the task of machine translation (MT) of low-resource languages remains a challenge. Neural MT systems can be trained in an unsupervised way without any translation resources but the quality lags behind, especially in truly low-resource conditions. We propose a training strategy that relies on pseudo-parallel sentence pairs mined from monolingual corpora in addition to synthetic sentence pairs back-translated from monolingual corpora. We experiment with different training schedules and reach an improvement of up to 14.5 BLEU points (English to Ukrainian) over a baseline trained on back-translated data only.
The advent of large language models (LLMs) has gained tremendous attention over the past year. Previous studies have shown the astonishing performance of LLMs not only in other tasks but also in emotion recognition in terms of accuracy, universality, explanation, robustness, few/zero-shot learning, and others. Leveraging the capability of LLMs inevitably becomes an essential solution for emotion recognition. To this end, we further comprehensively investigate how LLMs perform in linguistic emotion recognition if we concentrate on this specific task. Specifically, we exemplify a publicly available and widely used LLM -- Chat General Language Model, and customise it for our target by using two different modal adaptation techniques, i.e., deep prompt tuning and low-rank adaptation. The experimental results obtained on six widely used datasets present that the adapted LLM can easily outperform other state-of-the-art but specialised deep models. This indicates the strong transferability and feasibility of LLMs in the field of emotion recognition.
Biomedical language understanding benchmarks are the driving forces for artificial intelligence applications with large language model (LLM) back-ends. However, most current benchmarks: (a) are limited to English which makes it challenging to replicate many of the successes in English for other languages, or (b) focus on knowledge probing of LLMs and neglect to evaluate how LLMs apply these knowledge to perform on a wide range of bio-medical tasks, or (c) have become a publicly available corpus and are leaked to LLMs during pre-training. To facilitate the research in medical LLMs, we re-build the Chinese Biomedical Language Understanding Evaluation (CBLUE) benchmark into a large scale prompt-tuning benchmark, PromptCBLUE. Our benchmark is a suitable test-bed and an online platform for evaluating Chinese LLMs' multi-task capabilities on a wide range bio-medical tasks including medical entity recognition, medical text classification, medical natural language inference, medical dialogue understanding and medical content/dialogue generation. To establish evaluation on these tasks, we have experimented and report the results with the current 9 Chinese LLMs fine-tuned with differtent fine-tuning techniques.
Curated datasets for healthcare are often limited due to the need of human annotations from experts. In this paper, we present MedEval, a multi-level, multi-task, and multi-domain medical benchmark to facilitate the development of language models for healthcare. MedEval is comprehensive and consists of data from several healthcare systems and spans 35 human body regions from 8 examination modalities. With 22,779 collected sentences and 21,228 reports, we provide expert annotations at multiple levels, offering a granular potential usage of the data and supporting a wide range of tasks. Moreover, we systematically evaluated 10 generic and domain-specific language models under zero-shot and finetuning settings, from domain-adapted baselines in healthcare to general-purposed state-of-the-art large language models (e.g., ChatGPT). Our evaluations reveal varying effectiveness of the two categories of language models across different tasks, from which we notice the importance of instruction tuning for few-shot usage of large language models. Our investigation paves the way toward benchmarking language models for healthcare and provides valuable insights into the strengths and limitations of adopting large language models in medical domains, informing their practical applications and future advancements.
This paper presents the system submitted by the team from IIT(ISM) Dhanbad in FIRE IRSE 2023 shared task 1 on the automatic usefulness prediction of code-comment pairs as well as the impact of Large Language Model(LLM) generated data on original base data towards an associated source code. We have developed a framework where we train a machine learning-based model using the neural contextual representations of the comments and their corresponding codes to predict the usefulness of code-comments pair and performance analysis with LLM-generated data with base data. In the official assessment, our system achieves a 4% increase in F1-score from baseline and the quality of generated data.
Large language models (LLMs) have recently reached an impressive level of linguistic capability, prompting comparisons with human language skills. However, there have been relatively few systematic inquiries into the linguistic capabilities of the latest generation of LLMs, and those studies that do exist (i) ignore the remarkable ability of humans to generalize, (ii) focus only on English, and (iii) investigate syntax or semantics and overlook other capabilities that lie at the heart of human language, like morphology. Here, we close these gaps by conducting the first rigorous analysis of the morphological capabilities of ChatGPT in four typologically varied languages (specifically, English, German, Tamil, and Turkish). We apply a version of Berko's (1958) wug test to ChatGPT, using novel, uncontaminated datasets for the four examined languages. We find that ChatGPT massively underperforms purpose-built systems, particularly in English. Overall, our results -- through the lens of morphology -- cast a new light on the linguistic capabilities of ChatGPT, suggesting that claims of human-like language skills are premature and misleading.
Self-supervised representation learning on text-attributed graphs, which aims to create expressive and generalizable representations for various downstream tasks, has received increasing research attention lately. However, existing methods either struggle to capture the full extent of structural context information or rely on task-specific training labels, which largely hampers their effectiveness and generalizability in practice. To solve the problem of self-supervised representation learning on text-attributed graphs, we develop a novel Graph-Centric Language model -- GRENADE. Specifically, GRENADE exploits the synergistic effect of both pre-trained language model and graph neural network by optimizing with two specialized self-supervised learning algorithms: graph-centric contrastive learning and graph-centric knowledge alignment. The proposed graph-centric self-supervised learning algorithms effectively help GRENADE to capture informative textual semantics as well as structural context information on text-attributed graphs. Through extensive experiments, GRENADE shows its superiority over state-of-the-art methods. Implementation is available at \url{https://github.com/bigheiniu/GRENADE}.
Thematic analysis (TA) has been widely used for analyzing qualitative data in many disciplines and fields. To ensure reliable analysis, the same piece of data is typically assigned to at least two human coders. Moreover, to produce meaningful and useful analysis, human coders develop and deepen their data interpretation and coding over multiple iterations, making TA labor-intensive and time-consuming. Recently the emerging field of large language models (LLMs) research has shown that LLMs have the potential replicate human-like behavior in various tasks: in particular, LLMs outperform crowd workers on text-annotation tasks, suggesting an opportunity to leverage LLMs on TA. We propose a human-LLM collaboration framework (i.e., LLM-in-the-loop) to conduct TA with in-context learning (ICL). This framework provides the prompt to frame discussions with a LLM (e.g., GPT-3.5) to generate the final codebook for TA. We demonstrate the utility of this framework using survey datasets on the aspects of the music listening experience and the usage of a password manager. Results of the two case studies show that the proposed framework yields similar coding quality to that of human coders but reduces TA's labor and time demands.
In this paper, we address the hallucination problem commonly found in natural language generation tasks. Language models often generate fluent and convincing content but can lack consistency with the provided source, resulting in potential inaccuracies. We propose a new decoding method called Fidelity-Enriched Contrastive Search (FECS), which augments the contrastive search framework with context-aware regularization terms. FECS promotes tokens that are semantically similar to the provided source while penalizing repetitiveness in the generated text. We demonstrate its effectiveness across two tasks prone to hallucination: abstractive summarization and dialogue generation. Results show that FECS consistently enhances faithfulness across various language model sizes while maintaining output diversity comparable to well-performing decoding algorithms.
Vocabulary tests, once a cornerstone of language modeling evaluation, have been largely overlooked in the current landscape of Large Language Models (LLMs) like Llama, Mistral, and GPT. While most LLM evaluation benchmarks focus on specific tasks or domain-specific knowledge, they often neglect the fundamental linguistic aspects of language understanding and production. In this paper, we advocate for the revival of vocabulary tests as a valuable tool for assessing LLM performance. We evaluate seven LLMs using two vocabulary test formats across two languages and uncover surprising gaps in their lexical knowledge. These findings shed light on the intricacies of LLM word representations, their learning mechanisms, and performance variations across models and languages. Moreover, the ability to automatically generate and perform vocabulary tests offers new opportunities to expand the approach and provide a more complete picture of LLMs' language skills.
Human gaze data offer cognitive information that reflects natural language comprehension. Indeed, augmenting language models with human scanpaths has proven beneficial for a range of NLP tasks, including language understanding. However, the applicability of this approach is hampered because the abundance of text corpora is contrasted by a scarcity of gaze data. Although models for the generation of human-like scanpaths during reading have been developed, the potential of synthetic gaze data across NLP tasks remains largely unexplored. We develop a model that integrates synthetic scanpath generation with a scanpath-augmented language model, eliminating the need for human gaze data. Since the model's error gradient can be propagated throughout all parts of the model, the scanpath generator can be fine-tuned to downstream tasks. We find that the proposed model not only outperforms the underlying language model, but achieves a performance that is comparable to a language model augmented with real human gaze data. Our code is publicly available.
E-commerce pre-sales dialogue aims to understand and elicit user needs and preferences for the items they are seeking so as to provide appropriate recommendations. Conversational recommender systems (CRSs) learn user representation and provide accurate recommendations based on dialogue context, but rely on external knowledge. Large language models (LLMs) generate responses that mimic pre-sales dialogues after fine-tuning, but lack domain-specific knowledge for accurate recommendations. Intuitively, the strengths of LLM and CRS in E-commerce pre-sales dialogues are complementary, yet no previous work has explored this. This paper investigates the effectiveness of combining LLM and CRS in E-commerce pre-sales dialogues, proposing two collaboration methods: CRS assisting LLM and LLM assisting CRS. We conduct extensive experiments on a real-world dataset of Ecommerce pre-sales dialogues. We analyze the impact of two collaborative approaches with two CRSs and two LLMs on four tasks of Ecommerce pre-sales dialogue. We find that collaborations between CRS and LLM can be very effective in some cases.