Emmanuelle Salin

Björn Nieth, Marianna Gracheva, Michaela Mahlberg et al.

While factual correctness and task-performance have been in focus of Large Language Model (LLM) research for a long time, the fundamental question of how human-like generated texts are on a linguistic level has been underexplored. From a corpus-linguistic perspective, language production is inherently context-dependent, with distinct communicative contexts giving rise to differences in frequencies and co-occurrence patterns of linguistic features. A text failing to adhere to these patterns can be content-wise correct, but still be unfavorable to human readers. In this work, we propose a context-aware evaluation framework in which human-likeness is assessed using a two-sample problem between the linguistic feature distribution of a human reference corpus for a given register and a corresponding LLM-generated corpus. We implement this framework using the Maximum Mean Discrepancy (MMD) and the 67 lexico-grammatical features introduced by Biber, which are commonly applied in corpus linguistics. In our experiments, we compare seven instruction-tuned, open-source models across five English-language datasets spanning distinct registers against a human baseline. While across all tested setups, LLMs deviate from the human baseline, which models are closest to human language depends on the register and is not dictated by model size.

Mitja Nikolaus, Emmanuelle Salin, Stephane Ayache et al.

Recent advances in vision-and-language modeling have seen the development of Transformer architectures that achieve remarkable performance on multimodal reasoning tasks. Yet, the exact capabilities of these black-box models are still poorly understood. While much of previous work has focused on studying their ability to learn meaning at the word-level, their ability to track syntactic dependencies between words has received less attention. We take a first step in closing this gap by creating a new multimodal task targeted at evaluating understanding of predicate-noun dependencies in a controlled setup. We evaluate a range of state-of-the-art models and find that their performance on the task varies considerably, with some models performing relatively well and others at chance level. In an effort to explain this variability, our analyses indicate that the quality (and not only sheer quantity) of pretraining data is essential. Additionally, the best performing models leverage fine-grained multimodal pretraining objectives in addition to the standard image-text matching objectives. This study highlights that targeted and controlled evaluations are a crucial step for a precise and rigorous test of the multimodal knowledge of vision-and-language models.

Gregory Senay, Emmanuelle Salin

This paper presents Masked ELMo, a new RNN-based model for language model pre-training, evolved from the ELMo language model. Contrary to ELMo which only uses independent left-to-right and right-to-left contexts, Masked ELMo learns fully bidirectional word representations. To achieve this, we use the same Masked language model objective as BERT. Additionally, thanks to optimizations on the LSTM neuron, the integration of mask accumulation and bidirectional truncated backpropagation through time, we have increased the training speed of the model substantially. All these improvements make it possible to pre-train a better language model than ELMo while maintaining a low computational cost. We evaluate Masked ELMo by comparing it to ELMo within the same protocol on the GLUE benchmark, where our model outperforms significantly ELMo and is competitive with transformer approaches.