Large Language Models (LLMs) frequently hallucinate, impeding their reliability in mission-critical situations.One approach to address this issue is to provide citations to relevant sources alongside generated content, enhancing the verifiability of generations.However, citing passages accurately in answers remains a substantial challenge.This paper proposes a weakly-supervised fine-tuning method leveraging factual consistency models (FCMs).Our approach alternates between generating texts with citations and supervised fine-tuning with FCM-filtered citation data.Focused learning is integrated into the objective, directing the fine-tuning process to emphasise the factual unit tokens, as measured by an FCM.Results on the ALCE few-shot citation benchmark with various instruction-tuned LLMs demonstrate superior performance compared to in-context learning, vanilla supervised fine-tuning, and state-of-the-art methods, with an average improvement of 34.1, 15.5, and 10.5 citation F 1 points, respectively.Moreover, in a domain transfer setting we show that the obtained citation generation ability robustly transfers to unseen datasets.Notably, our citation improvements contribute to the lowest factual error rate across baselines.

Deep learning-based Natural Language Processing (NLP) models are vulnerable to adversarial attacks, where small perturbations can cause a model to misclassify.Adversarial Training (AT) is often used to increase model robustness.However, we have discovered an intriguing phenomenon: deliberately or accidentally miscalibrating models masks gradients in a way that interferes with adversarial attack search methods, giving rise to an apparent increase in robustness.We show that this observed gain in robustness is an illusion of robustness (IOR), and demonstrate how an adversary can perform various forms of test-time temperature calibration to nullify the aforementioned interference and allow the adversarial attack to find adversarial examples.Hence, we urge the NLP community to incorporate test-time temperature scaling into their robustness evaluations to ensure that any observed gains are genuine.Finally, we show how the temperature can be scaled during training to improve genuine robustness.* Equal contribution.This paper reports on the work VR did whilst at Amazon Web Services.VC holds concurrent appointments as an Amazon Scholar and as a faculty at EPFL.This paper describes the work performed at Amazon.

Shiqi Wang, Zheng Li, Haifeng Qian, Chenghao Yang, Zijian Wang, Mingyue Shang, Varun Kumar, Samson Tan, Baishakhi Ray, Parminder Bhatia, Ramesh Nallapati, Murali Krishna Ramanathan, Dan Roth, Bing Xiang. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

Numerous visio-linguistic (V+L) representation learning methods have been developed, yet existing datasets do not adequately evaluate the extent to which they represent visual and linguistic concepts in a unified space.We propose several novel evaluation settings for V+L models, including cross-modal transfer.Furthermore, existing V+L benchmarks often report global accuracy scores on the entire dataset, making it difficult to pinpoint the specific reasoning tasks that models fail and succeed at.We present TRAVLR, a synthetic dataset comprising four V+L reasoning tasks.TRAVLR's synthetic nature allows us to constrain its training and testing distributions along task-relevant dimensions, enabling the evaluation of out-of-distribution generalisation.Each example in TRAVLR redundantly encodes the scene in two modalities, allowing either to be dropped or added during training or testing without losing relevant information.We compare the performance of four state-ofthe-art V+L models, finding that while they perform well on test examples from the same modality, they all fail at cross-modal transfer and have limited success accommodating the addition or deletion of one modality.We release TRAVLR as an open challenge for the research community.1

Large language models of code (Code-LLMs) have recently brought tremendous advances to code completion, a fundamental feature of programming assistance and code intelligence. However, most existing works ignore the possible presence of bugs in the code context for generation, which are inevitable in software development. Therefore, we introduce and study the buggy-code completion problem, inspired by the realistic scenario of real-time code suggestion where the code context contains potential bugs – anti-patterns that can become bugs in the completed program. To systematically study the task, we introduce two datasets: one with synthetic bugs derived from semantics-altering operator changes (buggy-HumanEval) and one with realistic bugs derived from user submissions to coding problems (buggy-FixEval). We find that the presence of potential bugs significantly degrades the generation performance of the high-performing Code-LLMs. For instance, the passing rates of CODEGEN-2B-MONO on test cases of buggy-HumanEval drop more than 50% given a single potential bug in the context. Finally, we investigate several post-hoc methods for mitigating the adverse effect of potential bugs and find that there remains a large gap in post-mitigation performance.

Samson Tan, Shafiq Joty, Kathy Baxter, Araz Taeihagh, Gregory A. Bennett, Min-Yen Kan. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Multilingual models have demonstrated impressive cross-lingual transfer performance.However, test sets like XNLI are monolingual at the example level.In multilingual communities, it is common for polyglots to code-mix when conversing with each other.Inspired by this phenomenon, we present two strong blackbox adversarial attacks (one word-level, one phrase-level) for multilingual models that push their ability to handle code-mixed sentences to the limit.The former uses bilingual dictionaries to propose perturbations and translations of the clean example for sense disambiguation.The latter directly aligns the clean example with its translations before extracting phrases as perturbations.Our phrase-level attack has a success rate of 89.75% against XLM-R large , bringing its average accuracy of 79.85 down to 8.18 on XNLI.Finally, we propose an efficient adversarial training scheme that trains in the same number of steps as the original model and show that it improves model accuracy.1 Original P: The girl that can help me is all the way across town.H: There is no one who can help me.Adversary P: olan girl that can help me is all the way across town.H: one who can help me.

Training on only perfect Standard English corpora predisposes pre-trained neural networks to discriminate against minorities from nonstandard linguistic backgrounds (e.g., African American Vernacular English, Colloquial Singapore English, etc.).We perturb the inflectional morphology of words to craft plausible and semantically similar adversarial examples that expose these biases in popular NLP models, e.g., BERT and Transformer, and show that adversarially fine-tuning them for a single epoch significantly improves robustness without sacrificing performance on clean data. 1

Inflectional variation is a common feature of World Englishes such as Colloquial Singapore English and African American Vernacular English.Although comprehension by human readers is usually unimpaired by nonstandard inflections, current NLP systems are not yet robust.We propose Base-Inflection Encoding (BITE), a method to tokenize English text by reducing inflected words to their base forms before reinjecting the grammatical information as special symbols.Fine-tuning pretrained NLP models for downstream tasks using our encoding defends against inflectional adversaries while maintaining performance on clean data.Models using BITE generalize better to dialects with non-standard inflections without explicit training and translation models converge faster when trained with BITE.Finally, we show that our encoding improves the vocabulary efficiency of popular data-driven subword tokenizers.Since there has been no prior work on quantitatively evaluating vocabulary efficiency, we propose metrics to do so. 1