CaLMQA: Exploring culturally specific long-form question answering across 23 languages

Large language models (LLMs) are commonly used for long-form question answering, which requires them to generate paragraph-length answers to complex questions. While long-form QA has been well-studied in English via many different datasets and evaluation metrics, this research has not been extended to cover most other languages. To bridge this gap, we introduce CaLMQA, a collection of 2.6K complex questions spanning 23 languages, including under-resourced, rarely-studied languages such as Fijian and Kirundi. Our dataset includes both naturally-occurring questions collected from community web forums as well as questions written by native speakers, whom we hire for this purpose. Our process yields diverse, complex questions that reflect cultural topics (e.g. traditions, laws, news) and the language usage of native speakers. We conduct automatic evaluation across a suite of open- and closed-source models using our novel metric CaLMScore, which detects incorrect language and token repetitions in answers, and observe that the quality of LLM-generated answers degrades significantly for some low-resource languages. We perform human evaluation on a subset of models and see that model performance is significantly worse for culturally specific questions than for culturally agnostic questions. Our findings highlight the need for further research in LLM multilingual capabilities and non-English LFQA evaluation.

One Thousand and One Pairs: A "novel" challenge for long-context language models

Synthetic long-context LLM benchmarks (e.g., "needle-in-the-haystack") test only surface-level retrieval capabilities, but how well can long-context LLMs retrieve, synthesize, and reason over information across book-length inputs? We address this question by creating NoCha, a dataset of 1,001 minimally different pairs of true and false claims about 67 recently-published English fictional books, written by human readers of those books. In contrast to existing long-context benchmarks, our annotators confirm that the largest share of pairs in NoCha require global reasoning over the entire book to verify. Our experiments show that while human readers easily perform this task, it is enormously challenging for all ten long-context LLMs that we evaluate: no open-weight model performs above random chance (despite their strong performance on synthetic benchmarks), while GPT-4o achieves the highest accuracy at 55.8%. Further analysis reveals that (1) on average, models perform much better on pairs that require only sentence-level retrieval vs. global reasoning; (2) model-generated explanations for their decisions are often inaccurate even for correctly-labeled claims; and (3) models perform substantially worse on speculative fiction books that contain extensive world-building. The methodology proposed in NoCha allows for the evolution of the benchmark dataset and the easy analysis of future models.

Error Span Annotation: A Balanced Approach for Human Evaluation of Machine Translation

High-quality Machine Translation (MT) evaluation relies heavily on human judgments. Comprehensive error classification methods, such as Multidimensional Quality Metrics (MQM), are expensive as they are time-consuming and can only be done by experts, whose availability may be limited especially for low-resource languages. On the other hand, just assigning overall scores, like Direct Assessment (DA), is simpler and faster and can be done by translators of any level, but are less reliable. In this paper, we introduce Error Span Annotation (ESA), a human evaluation protocol which combines the continuous rating of DA with the high-level error severity span marking of MQM. We validate ESA by comparing it to MQM and DA for 12 MT systems and one human reference translation (English to German) from WMT23. The results show that ESA offers faster and cheaper annotations than MQM at the same quality level, without the requirement of expensive MQM experts.

FABLES: Evaluating faithfulness and content selection in book-length summarization

While long-context large language models (LLMs) can technically summarize book-length documents (>100K tokens), the length and complexity of the documents have so far prohibited evaluations of input-dependent aspects like faithfulness. In this paper, we conduct the first large-scale human evaluation of faithfulness and content selection on LLM-generated summaries of fictional books. Our study mitigates the issue of data contamination by focusing on summaries of books published in 2023 or 2024, and we hire annotators who have fully read each book prior to the annotation task to minimize cost and cognitive burden. We collect FABLES, a dataset of annotations on 3,158 claims made in LLM-generated summaries of 26 books, at a cost of $5.2K USD, which allows us to rank LLM summarizers based on faithfulness: Claude-3-Opus significantly outperforms all closed-source LLMs, while the open-source Mixtral is on par with GPT-3.5-Turbo. An analysis of the annotations reveals that most unfaithful claims relate to events and character states, and they generally require indirect reasoning over the narrative to invalidate. While LLM-based auto-raters have proven reliable for factuality and coherence in other settings, we implement several LLM raters of faithfulness and find that none correlates strongly with human annotations, especially with regard to detecting unfaithful claims. Our experiments suggest that detecting unfaithful claims is an important future direction not only for summarization evaluation but also as a testbed for long-context understanding. Finally, we move beyond faithfulness by exploring content selection errors in book-length summarization: we develop a typology of omission errors related to crucial narrative elements and also identify a systematic over-emphasis on events occurring towards the end of the book.

Aurora-M: The First Open Source Multilingual Language Model Red-teamed according to the U.S. Executive Order

Pretrained language models underpin several AI applications, but their high computational cost for training limits accessibility. Initiatives such as BLOOM and StarCoder aim to democratize access to pretrained models for collaborative community development. However, such existing models face challenges: limited multilingual capabilities, continual pretraining causing catastrophic forgetting, whereas pretraining from scratch is computationally expensive, and compliance with AI safety and development laws. This paper presents Aurora-M, a 15B parameter multilingual open-source model trained on English, Finnish, Hindi, Japanese, Vietnamese, and code. Continually pretrained from StarCoderPlus on 435 billion additional tokens, Aurora-M surpasses 2 trillion tokens in total training token count. It is the first open-source multilingual model fine-tuned on human-reviewed safety instructions, thus aligning its development not only with conventional red-teaming considerations, but also with the specific concerns articulated in the Biden-Harris Executive Order on the Safe, Secure, and Trustworthy Development and Use of Artificial Intelligence. Aurora-M is rigorously evaluated across various tasks and languages, demonstrating robustness against catastrophic forgetting and outperforming alternatives in multilingual settings, particularly in safety evaluations. To promote responsible open-source LLM development, Aurora-M and its variants are released at https://huggingface.co/collections/aurora-m/aurora-m-models-65fdfdff62471e09812f5407 .

Large language models effectively leverage document-level context for literary translation, but critical errors persist

Large language models (LLMs) are competitive with the state of the art on a wide range of sentence-level translation datasets. However, their ability to translate paragraphs and documents remains unexplored because evaluation in these settings is costly and difficult. We show through a rigorous human evaluation that asking the Gpt-3.5 (text-davinci-003) LLM to translate an entire literary paragraph (e.g., from a novel) at once results in higher-quality translations than standard sentence-by-sentence translation across 18 linguistically-diverse language pairs (e.g., translating into and out of Japanese, Polish, and English). Our evaluation, which took approximately 350 hours of effort for annotation and analysis, is conducted by hiring translators fluent in both the source and target language and asking them to provide both span-level error annotations as well as preference judgments of which system's translations are better. We observe that discourse-level LLM translators commit fewer mistranslations, grammar errors, and stylistic inconsistencies than sentence-level approaches. With that said, critical errors still abound, including occasional content omissions, and a human translator's intervention remains necessary to ensure that the author's voice remains intact. We publicly release our dataset and error annotations to spur future research on evaluation of document-level literary translation.

Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense

To detect the deployment of large language models for malicious use cases (e.g., fake content creation or academic plagiarism), several approaches have recently been proposed for identifying AI-generated text via watermarks or statistical irregularities. How robust are these detection algorithms to paraphrases of AI-generated text? To stress test these detectors, we first train an 11B parameter paraphrase generation model (DIPPER) that can paraphrase paragraphs, optionally leveraging surrounding text (e.g., user-written prompts) as context. DIPPER also uses scalar knobs to control the amount of lexical diversity and reordering in the paraphrases. Paraphrasing text generated by three large language models (including GPT3.5-davinci-003) with DIPPER successfully evades several detectors, including watermarking, GPTZero, DetectGPT, and OpenAI's text classifier. For example, DIPPER drops the detection accuracy of DetectGPT from 70.3% to 4.6% (at a constant false positive rate of 1%), without appreciably modifying the input semantics. To increase the robustness of AI-generated text detection to paraphrase attacks, we introduce a simple defense that relies on retrieving semantically-similar generations and must be maintained by a language model API provider. Given a candidate text, our algorithm searches a database of sequences previously generated by the API, looking for sequences that match the candidate text within a certain threshold. We empirically verify our defense using a database of 15M generations from a fine-tuned T5-XXL model and find that it can detect 80% to 97% of paraphrased generations across different settings, while only classifying 1% of human-written sequences as AI-generated. We will open source our code, model and data for future research.

DEMETR: Diagnosing Evaluation Metrics for Translation

While machine translation evaluation metrics based on string overlap (e.g., BLEU) have their limitations, their computations are transparent: the BLEU score assigned to a particular candidate translation can be traced back to the presence or absence of certain words. The operations of newer learned metrics (e.g., BLEURT, COMET), which leverage pretrained language models to achieve higher correlations with human quality judgments than BLEU, are opaque in comparison. In this paper, we shed light on the behavior of these learned metrics by creating DEMETR, a diagnostic dataset with 31K English examples (translated from 10 source languages) for evaluating the sensitivity of MT evaluation metrics to 35 different linguistic perturbations spanning semantic, syntactic, and morphological error categories. All perturbations were carefully designed to form minimal pairs with the actual translation (i.e., differ in only one aspect). We find that learned metrics perform substantially better than string-based metrics on DEMETR. Additionally, learned metrics differ in their sensitivity to various phenomena (e.g., BERTScore is sensitive to untranslated words but relatively insensitive to gender manipulation, while COMET is much more sensitive to word repetition than to aspectual changes). We publicly release DEMETR to spur more informed future development of machine translation evaluation metrics

Exploring Document-Level Literary Machine Translation with Parallel Paragraphs from World Literature

Literary translation is a culturally significant task, but it is bottlenecked by the small number of qualified literary translators relative to the many untranslated works published around the world. Machine translation (MT) holds potential to complement the work of human translators by improving both training procedures and their overall efficiency. Literary translation is less constrained than more traditional MT settings since translators must balance meaning equivalence, readability, and critical interpretability in the target language. This property, along with the complex discourse-level context present in literary texts, also makes literary MT more challenging to computationally model and evaluate. To explore this task, we collect a dataset (Par3) of non-English language novels in the public domain, each aligned at the paragraph level to both human and automatic English translations. Using Par3, we discover that expert literary translators prefer reference human translations over machine-translated paragraphs at a rate of 84%, while state-of-the-art automatic MT metrics do not correlate with those preferences. The experts note that MT outputs contain not only mistranslations, but also discourse-disrupting errors and stylistic inconsistencies. To address these problems, we train a post-editing model whose output is preferred over normal MT output at a rate of 69% by experts. We publicly release Par3 at https://github.com/katherinethai/par3/ to spur future research into literary MT.

ezCoref: Towards Unifying Annotation Guidelines for Coreference Resolution

Large-scale, high-quality corpora are critical for advancing research in coreference resolution. However, existing datasets vary in their definition of coreferences and have been collected via complex and lengthy guidelines that are curated for linguistic experts. These concerns have sparked a growing interest among researchers to curate a unified set of guidelines suitable for annotators with various backgrounds. In this work, we develop a crowdsourcing-friendly coreference annotation methodology, ezCoref, consisting of an annotation tool and an interactive tutorial. We use ezCoref to re-annotate 240 passages from seven existing English coreference datasets (spanning fiction, news, and multiple other domains) while teaching annotators only cases that are treated similarly across these datasets. Surprisingly, we find that reasonable quality annotations were already achievable (>90% agreement between the crowd and expert annotations) even without extensive training. On carefully analyzing the remaining disagreements, we identify the presence of linguistic cases that our annotators unanimously agree upon but lack unified treatments (e.g., generic pronouns, appositives) in existing datasets. We propose the research community should revisit these phenomena when curating future unified annotation guidelines.