Lies, Damned Lies, and Distributional Language Statistics: Persuasion and Deception with Large Language Models

Large Language Models (LLMs) can generate content that is as persuasive as human-written text and appear capable of selectively producing deceptive outputs. These capabilities raise concerns about potential misuse and unintended consequences as these systems become more widely deployed. This review synthesizes recent empirical work examining LLMs' capacity and proclivity for persuasion and deception, analyzes theoretical risks that could arise from these capabilities, and evaluates proposed mitigations. While current persuasive effects are relatively small, various mechanisms could increase their impact, including fine-tuning, multimodality, and social factors. We outline key open questions for future research, including how persuasive AI systems might become, whether truth enjoys an inherent advantage over falsehoods, and how effective different mitigation strategies may be in practice.

Why do language models perform worse for morphologically complex languages?

Language models perform differently across languages. It has been previously suggested that morphological typology may explain some of this variability (Cotterell et al., 2018). We replicate previous analyses and find additional new evidence for a performance gap between agglutinative and fusional languages, where fusional languages, such as English, tend to have better language modeling performance than morphologically more complex languages like Turkish. We then propose and test three possible causes for this performance gap: morphological alignment of tokenizers, tokenization quality, and disparities in dataset sizes and measurement. To test the morphological alignment hypothesis, we present MorphScore, a tokenizer evaluation metric, and supporting datasets for 22 languages. We find some evidence that tokenization quality explains the performance gap, but none for the role of morphological alignment. Instead we find that the performance gap is most reduced when training datasets are of equivalent size across language types, but only when scaled according to the so-called "byte-premium" -- the different encoding efficiencies of different languages and orthographies. These results suggest that no language is harder or easier for a language model to learn on the basis of its morphological typology. Differences in performance can be attributed to disparities in dataset size. These results bear on ongoing efforts to improve performance for low-performing and under-resourced languages.

Goldfish: Monolingual Language Models for 350 Languages

For many low-resource languages, the only available language models are large multilingual models trained on many languages simultaneously. However, using FLORES perplexity as a metric, we find that these models perform worse than bigrams for many languages (e.g. 24% of languages in XGLM 4.5B; 43% in BLOOM 7.1B). To facilitate research that focuses on low-resource languages, we pre-train and release Goldfish, a suite of monolingual autoregressive Transformer language models up to 125M parameters for 350 languages. The Goldfish reach lower FLORES perplexities than BLOOM, XGLM, and MaLA-500 on 98 of 204 FLORES languages, despite each Goldfish model being over 10x smaller. However, the Goldfish significantly underperform larger multilingual models on reasoning benchmarks, suggesting that for low-resource languages, multilinguality primarily improves general reasoning abilities rather than basic text generation. We release models trained on 5MB (350 languages), 10MB (288 languages), 100MB (166 languages), and 1GB (83 languages) of text data where available. The Goldfish models are available as baselines, fine-tuning sources, or augmentations to existing models in low-resource NLP research, and they are further useful for crosslinguistic studies requiring maximally comparable models across languages.

GPT-4 is judged more human than humans in displaced and inverted Turing tests

Everyday AI detection requires differentiating between people and AI in informal, online conversations. In many cases, people will not interact directly with AI systems but instead read conversations between AI systems and other people. We measured how well people and large language models can discriminate using two modified versions of the Turing test: inverted and displaced. GPT-3.5, GPT-4, and displaced human adjudicators judged whether an agent was human or AI on the basis of a Turing test transcript. We found that both AI and displaced human judges were less accurate than interactive interrogators, with below chance accuracy overall. Moreover, all three judged the best-performing GPT-4 witness to be human more often than human witnesses. This suggests that both humans and current LLMs struggle to distinguish between the two when they are not actively interrogating the person, underscoring an urgent need for more accurate tools to detect AI in conversations.

Dissecting the Ullman Variations with a SCALPEL: Why do LLMs fail at Trivial Alterations to the False Belief Task?

Recent empirical results have sparked a debate about whether or not Large Language Models (LLMs) are capable of Theory of Mind (ToM). While some have found LLMs to be successful on ToM evaluations such as the False Belief task (Kosinski, 2023), others have argued that LLMs solve these tasks by exploiting spurious correlations -- not representing beliefs -- since they fail on trivial alterations to these tasks (Ullman, 2023). In this paper, we introduce SCALPEL: a technique to generate targeted modifications for False Belief tasks to test different specific hypotheses about why LLMs fail. We find that modifications which make explicit common inferences -- such as that looking at a transparent object implies recognizing its contents -- preserve LLMs' performance. This suggests that LLMs' failures on modified ToM tasks could result from a lack of more general commonsense reasoning, rather than a failure to represent mental states. We argue that SCALPEL could be helpful for explaining LLM successes and failures in other cases.

People cannot distinguish GPT-4 from a human in a Turing test

We evaluated 3 systems (ELIZA, GPT-3.5 and GPT-4) in a randomized, controlled, and preregistered Turing test. Human participants had a 5 minute conversation with either a human or an AI, and judged whether or not they thought their interlocutor was human. GPT-4 was judged to be a human 54% of the time, outperforming ELIZA (22%) but lagging behind actual humans (67%). The results provide the first robust empirical demonstration that any artificial system passes an interactive 2-player Turing test. The results have implications for debates around machine intelligence and, more urgently, suggest that deception by current AI systems may go undetected. Analysis of participants' strategies and reasoning suggests that stylistic and socio-emotional factors play a larger role in passing the Turing test than traditional notions of intelligence.

Revenge of the Fallen? Recurrent Models Match Transformers at Predicting Human Language Comprehension Metrics

Transformers have supplanted Recurrent Neural Networks as the dominant architecture for both natural language processing tasks and, despite criticisms of cognitive implausibility, for modelling the effect of predictability on online human language comprehension. However, two recently developed recurrent neural network architectures, RWKV and Mamba, appear to perform natural language tasks comparably to or better than transformers of equivalent scale. In this paper, we show that contemporary recurrent models are now also able to match - and in some cases, exceed - performance of comparably sized transformers at modeling online human language comprehension. This suggests that transformer language models are not uniquely suited to this task, and opens up new directions for debates about the extent to which architectural features of language models make them better or worse models of human language comprehension.

A Bit of a Problem: Measurement Disparities in Dataset Sizes Across Languages

How should text dataset sizes be compared across languages? Even for content-matched (parallel) corpora, UTF-8 encoded text can require a dramatically different number of bytes for different languages. In our work, we define the byte premium between two languages as the ratio of bytes used to encode content-matched text in those languages. We compute byte premiums for 1155 languages, and we use linear regressions to estimate byte premiums for other languages. We release a tool to obtain byte premiums for any two languages, enabling comparisons of dataset sizes across languages for more equitable multilingual model development and data practices.

When Is Multilinguality a Curse? Language Modeling for 250 High- and Low-Resource Languages

Multilingual language models are widely used to extend NLP systems to low-resource languages. However, concrete evidence for the effects of multilinguality on language modeling performance in individual languages remains scarce. Here, we pre-train over 10,000 monolingual and multilingual language models for over 250 languages, including multiple language families that are under-studied in NLP. We assess how language modeling performance in each language varies as a function of (1) monolingual dataset size, (2) added multilingual dataset size, (3) linguistic similarity of the added languages, and (4) model size (up to 45M parameters). We find that in moderation, adding multilingual data improves low-resource language modeling performance, similar to increasing low-resource dataset sizes by up to 33%. Improvements depend on the syntactic similarity of the added multilingual data, with marginal additional effects of vocabulary overlap. However, high-resource languages consistently perform worse in multilingual pre-training scenarios. As dataset sizes increase, adding multilingual data begins to hurt performance for both low-resource and high-resource languages, likely due to limited model capacity (the "curse of multilinguality"). These results suggest that massively multilingual pre-training may not be optimal for any languages involved, but that more targeted models can significantly improve performance.

Structural Priming Demonstrates Abstract Grammatical Representations in Multilingual Language Models

Abstract grammatical knowledge - of parts of speech and grammatical patterns - is key to the capacity for linguistic generalization in humans. But how abstract is grammatical knowledge in large language models? In the human literature, compelling evidence for grammatical abstraction comes from structural priming. A sentence that shares the same grammatical structure as a preceding sentence is processed and produced more readily. Because confounds exist when using stimuli in a single language, evidence of abstraction is even more compelling from crosslingual structural priming, where use of a syntactic structure in one language primes an analogous structure in another language. We measure crosslingual structural priming in large language models, comparing model behavior to human experimental results from eight crosslingual experiments covering six languages, and four monolingual structural priming experiments in three non-English languages. We find evidence for abstract monolingual and crosslingual grammatical representations in the models that function similarly to those found in humans. These results demonstrate that grammatical representations in multilingual language models are not only similar across languages, but they can causally influence text produced in different languages.