Reasoning methods, best exemplified by the well-known Chain-of-Thought (CoT), empower the reasoning abilities of Large Language Models (LLMs) by eliciting them to solve complex tasks in a step-by-step manner. Although they are achieving significant success, the ability to deliver multi-step reasoning remains limited to English because of the imbalance in the distribution of pre-training data, which makes other languages a barrier. In this paper, we propose Cross-lingual Tree-of-Thoughts (Cross-ToT), a method for aligning Cross-lingual CoT reasoning across languages. The proposed method, through a self-consistent cross-lingual prompting mechanism inspired by the Tree-of-Thoughts approach, provides multi-step reasoning paths in different languages that, during the steps, lead to the final solution. Experimental evaluations show that our method significantly outperforms existing prompting methods by reducing the number of interactions and achieving state-of-the-art performance.

The language ability of Large Language Models (LLMs) is often unbalanced towards English because of the imbalance in the distribution of the pre-training data. This disparity is demanded in further fine-tuning and affecting the cross-lingual abilities of LLMs. In this paper, we propose to empower Instruction-tuned LLMs (It-LLMs) in languages other than English by building semantic alignment between them. Hence, we propose CrossAlpaca, an It-LLM with cross-lingual Instruction-following and Translation-following demonstrations to improve semantic alignment between languages. We validate our approach on the multilingual Question Answering (QA) benchmarks XQUAD and MLQA and adapted versions of MMLU and BBH.Our models, tested over six different languages, outperform the It-LLMs tuned on monolingual data. The final results show that instruction tuning on non-English data is not enough and that semantic alignment can be further improved by Translation-following demonstrations.

Understanding textual description to generate code seems to be an achieved capability of instruction-following Large Language Models (LLMs) in zero-shot scenario. However, there is a severe possibility that this translation ability may be influenced by having seen target textual descriptions and the related code. This effect is known as Data Contamination.In this study, we investigate the impact of Data Contamination on the performance of GPT-3.5 in the Text-to-SQL code-generating tasks. Hence, we introduce a novel method to detect Data Contamination in GPTs and examine GPT-3.5’s Text-to-SQL performances using the known Spider Dataset and our new unfamiliar dataset Termite. Furthermore, we analyze GPT-3.5’s efficacy on databases with modified information via an adversarial table disconnection (ATD) approach, complicating Text-to-SQL tasks by removing structural pieces of information from the database. Our results indicate a significant performance drop in GPT-3.5 on the unfamiliar Termite dataset, even with ATD modifications, highlighting the effect of Data Contamination on LLMs in Text-to-SQL translation tasks.

Large Language Models (LLMs) have been exhibiting outstanding abilities to reason around cognitive states, intentions, and reactions of all people involved, letting humans guide and comprehend day-to-day social interactions effectively. In fact, several multiple-choice questions (MCQ) benchmarks have been proposed to construct solid assessments of the models’ abilities. However, earlier works demonstrate the presence of inherent “order bias” in LLMs, posing challenges to the appropriate evaluation. In this paper, we investigate LLMs’ resilience abilities through a series of probing tests using four MCQ benchmarks. Introducing adversarial examples, we show a significant performance gap, mainly when varying the order of the choices, which reveals a selection bias and brings into discussion reasoning abilities. Following a correlation between first positions and model choices due to positional bias, we hypothesized the presence of structural heuristics in the decision-making process of the LLMs, strengthened by including significant examples in few-shot scenarios. Finally, by using the Chain-of-Thought (CoT) technique, we elicit the model to reason and mitigate the bias by obtaining more robust models.

Cheap-to-Build Very Large-Language Models (CtB-LLMs) with affordable training are emerging as the next big revolution in natural language processing and understanding. These CtB-LLMs are democratizing access to trainable Very Large-Language Models (VLLMs) and, thus, may represent the building blocks of many NLP systems solving downstream tasks. Hence, a little or a large bias in CtB-LLMs may cause huge harm. In this paper, we performed a large investigation of the bias of three families of CtB-LLMs, and we showed that debiasing techniques are effective and usable. Indeed, according to current tests, the LLaMA and the OPT families have an important bias in gender, race, religion, and profession. In contrast to the analysis for other LMMs, we discovered that bias depends not on the number of parameters but on the perplexity. Finally, the debiasing of OPT using LORA reduces bias up to 4.12 points in the normalized stereotype score.

Chain-of-Thought (CoT) prompting empowersthe reasoning abilities of Large Language Models (LLMs), eliciting them to solve complexreasoning tasks in a step-wise manner. However, these capabilities appear only in models with billions of parameters, which represent an entry barrier for many users who are constrained to operate on a smaller model scale, i.e., Small Language Models (SLMs). Although many companies are releasing LLMs of the same family with fewer parameters, these models tend not to preserve all the reasoning capabilities of the original models, including CoT reasoning.In this paper, we propose a method for aligning and transferring reasoning abilities between larger to smaller Language Models. By using an Instruction-tuning-CoT method, that is, an Instruction-tuning designed around CoT-Demonstrations, we enable the SLMs to generate multi-step controlled reasoned answers when they are elicited with the CoT mechanism. Hence, we instruct a smaller Language Model using outputs generated by more robust models belonging to the same family or not, evaluating the impact across different types of models. Results obtained on question-answering and mathematical reasoning benchmarks show that LMs instructed via the Instruction-tuning CoT method produced by LLMs outperform baselines within both in-domain and out-domain scenarios.

Curriculum Learning (CL) has been emerged as an effective technique for improving the performances and reducing the cost of pre-training Large Language Models (LLMs). The efficacy of CL demonstrated in different scenarios is in the training LLMs by organizing examples from the simplest to the most complex. Although improvements have been shown extensively, this approach was used for pre-training, leaving novel fine-tuning approaches such as instruction-tuning unexplored. In this paper, we propose a novel complexity measure to empower the instruction-tuning method using the CL paradigm. To complement previous works, we propose cognitively motivated measures to determine the complexity of training demonstrations used in the instruction-tuning paradigm. Hence, we experiment with the proposed heuristics first in English and then in other languages. The downstream results show that delivering training examples by complexity ranking is also effective for instruction tuning, as it improves downstream performance while reducing costs. Furthermore, the technique can be easily transferred to languages other than English, e.g., Italian and French, without any adaptation, maintaining functionality and effectiveness.

Instruction-Following Language Models (IFLMs) are promising and versatile tools for solving many downstream, information-seeking tasks. Given their success, there is an urgent need to have a shared resource to determine whether existing and new IFLMs are prone to produce biased language interactions. In this paper, we propose Prompt Association Test (P-AT): a new resource for testing the presence of social biases in IFLMs. P-AT stems from WEAT (Caliskan et al., 2017) and generalizes the notion of measuring social biases to IFLMs. Basically, we cast WEAT word tests in promptized classification tasks, and we associate a metric - the bias score. Our resource consists of 2310 prompts. We then experimented with several families of IFLMs discovering gender and race biases in all the analyzed models. We expect P-AT to be an important tool for quantifying bias across different dimensions and, therefore, for encouraging the creation of fairer IFLMs before their distortions have consequences in the real world.

The impressive achievements of transformers force NLP researchers to delve into how these models represent the underlying structure of natural language. In this paper, we propose a novel standpoint to investigate the above issue: using typological similarities among languages to observe how their respective monolingual models encode structural information. We aim to layer-wise compare transformers for typologically similar languages to observe whether these similarities emerge for particular layers. For this investigation, we propose to use Centered Kernel Alignment to measure similarity among weight matrices. We found that syntactic typological similarity is consistent with the similarity between the weights in the middle layers, which are the pretrained BERT layers to which syntax encoding is generally attributed. Moreover, we observe that a domain adaptation on semantically equivalent texts enhances this similarity among weight matrices.

Directly learning from complex examples is generally problematic for humans and machines. Indeed, a better strategy is exposing learners to examples in a reasonable, pedagogically-motivated order. Curriculum Learning (CL) has been proposed to import this strategy when training machine learning models. In this paper, building on Curriculum Learning, we propose a novel, linguistically motivated measure to determine example complexity for organizing examples during learning. Our complexity measure - LRC- is based on length, rarity, and comprehensibility. Our resulting learning model is CL-LRC, that is, CL with LRC. Experiments on downstream tasks show that CL-LRC outperforms existing CL and non-CL methods for training BERT and RoBERTa from scratch. Furthermore, we analyzed different measures, including perplexity, loss, and learning curve of different models pre-trained from scratch, showing that CL-LRC performs better than the state-of-the-art.

Pre-trained Transformers are challenging human performances in many Natural Language Processing tasks. The massive datasets used for pre-training seem to be the key to their success on existing tasks. In this paper, we explore how a range of pre-trained natural language understanding models performs on definitely unseen sentences provided by classification tasks over a DarkNet corpus. Surprisingly, results show that syntactic and lexical neural networks perform on par with pre-trained Transformers even after fine-tuning. Only after what we call extreme domain adaptation, that is, retraining with the masked language model task on all the novel corpus, pre-trained Transformers reach their standard high results. This suggests that huge pre-training corpora may give Transformers unexpected help since they are exposed to many of the possible sentences.

Large Language Models (LLMs) are impressive machines with the ability to memorize, possibly generalized learning examples. We present here a small, focused contribution to the analysis of the interplay between memorization and performance of BERT in downstream tasks. We propose PreCog, a measure for evaluating memorization from pre-training, and we analyze its correlation with the BERT’s performance. Our experiments show that highly memorized examples are better classified, suggesting memorization is an essential key to success for BERT.

Word embeddings are powerful dictionaries, which may easily capture language variations. However, these dictionaries fail to give sense to rare words, which are surprisingly often covered by traditional dictionaries. In this paper, we propose to use definitions retrieved in traditional dictionaries to produce word embeddings for rare words. For this purpose, we introduce two methods: Definition Neural Network (DefiNNet) and Define BERT (DefBERT). In our experiments, DefiNNet and DefBERT significantly outperform state-of-the-art as well as baseline methods devised for producing embeddings of unknown words. In fact, DefiNNet significantly outperforms FastText, which implements a method for the same task-based on n-grams, and DefBERT significantly outperforms the BERT method for OOV words. Then, definitions in traditional dictionaries are useful to build word embeddings for rare words.

Syntactic parsers have dominated natural language understanding for decades. Yet, their syntactic interpretations are losing centrality in downstream tasks due to the success of large-scale textual representation learners. In this paper, we propose KERMIT (Kernel-inspired Encoder with Recursive Mechanism for Interpretable Trees) to embed symbolic syntactic parse trees into artificial neural networks and to visualize how syntax is used in inference. We experimented with KERMIT paired with two state-of-the-art transformer-based universal sentence encoders (BERT and XLNet) and we showed that KERMIT can indeed boost their performance by effectively embedding human-coded universal syntactic representations in neural networks