TACL 2024 Papers

Cold-start active learning (CSAL) selects valuable instances from an unlabeled dataset for manual annotation. It provides high-quality data at a low annotation cost for label-scarce text classification. However, existing CSAL methods overlook weak classes and hard representative examples, resulting in biased learning. To address these issues, this paper proposes a novel dual-diversity enhancing and uncertainty-aware (DEUCE) framework for CSAL. Specifically, DEUCE leverages a pretrained language model (PLM) to efficiently extract textual representations, class predictions, and predictive uncertainty. Then, it constructs a Dual-Neighbor Graph (DNG) to combine information on both textual diversity and class diversity, ensuring a balanced data distribution. It further propagates uncertainty information via density-based clustering to select hard representative instances. DEUCE performs well in selecting class-balanced and hard representative data by dual-diversity and informativeness. Experiments on six NLP datasets demonstrate the superiority and efficiency of DEUCE.

Relation extraction has evolved from supervised relation extraction to zero-shot setting due to the continuous emergence of newly generated relations. Some pioneering works handle zero-shot relation extraction by reformulating it into proxy tasks, such as reading comprehension and textual entailment. Nonetheless, the divergence in proxy task formulations from relation extraction hinders the acquisition of informative semantic representations, leading to subpar performance. Therefore, in this paper, we take a data-driven view to handle zero-shot relation extraction under a three-step paradigm, including encoder training, relation clustering, and summarization. Specifically, to train a discriminative relational encoder, we propose a novel selective contrastive learning framework, namely, SCL, where selective importance scores are assigned to distinguish the importance of different negative contrastive instances. During testing, the prompt-based encoder is employed to map test samples into representation vectors, which are then clustered into several groups. Typical samples closest to the cluster centroid are selected for summarization to generate the predicted relation for all samples in the cluster. Moreover, we design a simple non-parametric threshold plugin to reduce false-positive errors in inference on unseen relation representations. Our experiments demonstrate that SCL outperforms the current state-of-the-art method by over 3% across all metrics.

Although commonsense reasoning is greatly shaped by cultural and geographical factors, previous studies have predominantly centered on cultures grounded in the English language, potentially resulting in an Anglocentric bias. In this paper, we introduce IndoCulture, aimed at understanding the influence of geographical factors on language model reasoning ability, with a specific emphasis on the diverse cultures found within eleven Indonesian provinces. In contrast to prior work that has relied on templates (Yin et al., 2022) and online scrapping (Fung et al., 2024), we create IndoCulture by asking local people to manually develop a cultural context and plausible options, across a set of predefined topics. Evaluation of 27 language models reveals several insights: (1) the open-weight Llama–3 is competitive with GPT–4, while other open-weight models struggle, with accuracies below 50%; (2) there is a general pattern of models generally performing better for some provinces, such as Bali and West Java, and less well for others; and (3) the inclusion of location context enhances performance, especially for larger models like GPT–4, emphasizing the significance of geographical context in commonsense reasoning.1

Retrieval Augmented Language Models (RALMs) have gained significant attention for their ability to generate accurate answers and improve efficiency. However, RALMs are inherently vulnerable to imperfect information due to their reliance on the imperfect retriever or knowledge source. We identify three common scenarios—unanswerable, adversarial, conflicting—where retrieved document sets can confuse RALMs with plausible real-world examples. We present the first comprehensive investigation to assess how well RALMs detect and handle such problematic scenarios. Among these scenarios, to systematically examine adversarial robustness we propose a new adversarial attack method, Generative model-based ADVersarial attack (GenADV) and a novel metric Robustness under Additional Document (RAD). Our findings reveal that RALMs often fail to identify the unanswerability or contradiction of a document set, which frequently leads to hallucinations. Moreover, we show that the addition of an adversary significantly degrades RALM’s performance, with the model becoming even more vulnerable when the two scenarios overlap (adversarial+ unanswerable). Our research identifies critical areas for assessing and enhancing the robustness of RALMs, laying the foundation for the development of more robust models.1

How much meaning influences gender assignment across languages is an active area of research in linguistics and cognitive science. We can view current approaches as aiming to determine where gender assignment falls on a spectrum, from being fully arbitrarily determined to being largely semantically determined. For the latter case, there is a formulation of the neo-Whorfian hypothesis, which claims that even inanimate noun gender influences how people conceive of and talk about objects (using the choice of adjective used to modify inanimate nouns as a proxy for meaning). We offer a novel, causal graphical model that jointly represents the interactions between a noun’s grammatical gender, its meaning, and adjective choice. In accordance with past results, we find a significant relationship between the gender of nouns and the adjectives that modify them. However, when we control for the meaning of the noun, the relationship between grammatical gender and adjective choice is near zero and insignificant.

Fact verification on tabular evidence incentivizes the use of symbolic reasoning models where a logical form is constructed (e.g., a LISP-style program), providing greater verifiability than fully neural approaches. However, these logical forms typically rely on well-formed tables, restricting their use in many scenarios. An emerging symbolic reasoning paradigm for textual evidence focuses on natural logic inference, which constructs proofs by modeling set-theoretic relations between a claim and its evidence in natural language. This approach provides flexibility and transparency but is less compatible with tabular evidence since the relations do not extend to arithmetic functions. We propose a set-theoretic interpretation of numerals and arithmetic functions in the context of natural logic, enabling the integration of arithmetic expressions in deterministic proofs. We leverage large language models to generate arithmetic expressions by generating questions about salient parts of a claim which are answered by executing appropriate functions on tables. In a few-shot setting on FEVEROUS, we achieve an accuracy of 71.4, outperforming both fully neural and symbolic reasoning models by 3.4 points. When evaluated on TabFact without any further training, our method remains competitive with an accuracy lead of 0.5 points.

We introduce Holmes, a new benchmark designed to assess language models’ (LMs’) linguistic competence—their unconscious understanding of linguistic phenomena. Specifically, we use classifier-based probing to examine LMs’ internal representations regarding distinct linguistic phenomena (e.g., part-of-speech tagging). As a result, we meet recent calls to disentangle LMs’ linguistic competence from other cognitive abilities, such as following instructions in prompting-based evaluations. Composing Holmes, we review over 270 probing studies and include more than 200 datasets to assess syntax, morphology, semantics, reasoning, and discourse phenomena. Analyzing over 50 LMs reveals that, aligned with known trends, their linguistic competence correlates with model size. However, surprisingly, model architecture and instruction tuning also significantly influence performance, particularly in morphology and syntax. Finally, we propose FlashHolmes, a streamlined version that reduces the computation load while maintaining high-ranking precision.

This paper introduces Filtered Corpus Training, a method that trains language models (LMs) on corpora with certain linguistic constructions filtered out from the training data, and uses it to measure the ability of LMs to perform linguistic generalization on the basis of indirect evidence. We apply the method to both LSTM and Transformer LMs (of roughly comparable size), developing filtered corpora that target a wide range of linguistic phenomena. Our results show that while transformers are better qua LMs (as measured by perplexity), both models perform equally and surprisingly well on linguistic generalization measures, suggesting that they are capable of generalizing from indirect evidence.

Training a task-oriented dialogue policy using deep reinforcement learning is promising but requires extensive environment exploration. The amount of wasted invalid exploration makes policy learning inefficient. In this paper, we define and argue that dead-end states are important reasons for invalid exploration. When a conversation enters a dead-end state, regardless of the actions taken afterward, it will continue in a dead-end trajectory until the agent reaches a termination state or maximum turn. We propose a Dead-end Detection and Resurrection (DDR) method that detects dead-end states in an efficient manner and provides a rescue action to guide and correct the exploration direction. To prevent dialogue policies from repeating errors, DDR also performs dialogue data augmentation by adding relevant experiences that include dead-end states and penalties into the experience pool. We first validate the dead-end detection reliability and then demonstrate the effectiveness and generality of the method across various domains through experiments on four public dialogue datasets.

Large Language Models (LLMs) have transformed natural language processing tasks successfully. Yet, their large size and high computational needs pose challenges for practical use, especially in resource-limited settings. Model compression has emerged as a key research area to address these challenges. This paper presents a survey of model compression techniques for LLMs. We cover methods like quantization, pruning, and knowledge distillation, highlighting recent advancements. We also discuss benchmarking strategies and evaluation metrics crucial for assessing compressed LLMs. This survey offers valuable insights for researchers and practitioners, aiming to enhance efficiency and real-world applicability of LLMs while laying a foundation for future advancements.

We propose a method for unsupervised abstractive opinion summarization, that combines the attributability and scalability of extractive approaches with the coherence and fluency of Large Language Models (LLMs). Our method, HIRO, learns an index structure that maps sentences to a path through a semantically organized discrete hierarchy. At inference time, we populate the index and use it to identify and retrieve clusters of sentences containing popular opinions from input reviews. Then, we use a pretrained LLM to generate a readable summary that is grounded in these extracted evidential clusters. The modularity of our approach allows us to evaluate its efficacy at each stage. We show that HIRO learns an encoding space that is more semantically structured than prior work, and generates summaries that are more representative of the opinions in the input reviews. Human evaluation confirms that HIRO generates significantly more coherent, detailed, and accurate summaries.

Recent large language model applications, such as Retrieval-Augmented Generation and chatbots, have led to an increased need to process longer input contexts. However, this requirement is hampered by inherent limitations. Architecturally, models are constrained by a context window defined during training. Additionally, processing extensive texts requires substantial GPU memory. We propose a novel approach, Finch, to compress the input context by leveraging the pre-trained model weights of the self-attention. Given a prompt and a long text, Finch iteratively identifies the most relevant Key (K) and Value (V) pairs over chunks of the text conditioned on the prompt. Only such pairs are stored in the KV cache, which, within the space constrained by the context window, ultimately contains a compressed version of the long text. Our proposal enables models to consume large inputs even with high compression (up to 93x) while preserving semantic integrity without the need for fine-tuning.

The rapid proliferation of large language models and natural language processing (NLP) applications creates a crucial need for uncertainty quantification to mitigate risks such as Hallucinations and to enhance decision-making reliability in critical applications. Conformal prediction is emerging as a theoretically sound and practically useful framework, combining flexibility with strong statistical guarantees. Its model-agnostic and distribution-free nature makes it particularly promising to address the current shortcomings of NLP systems that stem from the absence of uncertainty quantification. This paper provides a comprehensive survey of conformal prediction techniques, their guarantees, and existing applications in NLP, pointing to directions for future research and open challenges.

Human translators linger on some words and phrases more than others, and predicting this variation is a step towards explaining the underlying cognitive processes. Using data from the CRITT Translation Process Research Database, we evaluate the extent to which surprisal and attentional features derived from a Neural Machine Translation (NMT) model account for reading and production times of human translators. We find that surprisal and attention are complementary predictors of translation difficulty, and that surprisal derived from a NMT model is the single most successful predictor of production duration. Our analyses draw on data from hundreds of translators operating across 13 language pairs, and represent the most comprehensive investigation of human translation difficulty to date.

Several uncertainty estimation methods have been recently proposed for machine translation evaluation. While these methods can provide a useful indication of when not to trust model predictions, we show in this paper that the majority of them tend to underestimate model uncertainty, and as a result, they often produce misleading confidence intervals that do not cover the ground truth. We propose as an alternative the use of conformal prediction, a distribution-free method to obtain confidence intervals with a theoretically established guarantee on coverage. First, we demonstrate that split conformal prediction can “correct” the confidence intervals of previous methods to yield a desired coverage level, and we demonstrate these findings across multiple machine translation evaluation metrics and uncertainty quantification methods. Further, we highlight biases in estimated confidence intervals, reflected in imbalanced coverage for different attributes, such as the language and the quality of translations. We address this by applying conditional conformal prediction techniques to obtain calibration subsets for each data subgroup, leading to equalized coverage. Overall, we show that, provided access to a calibration set, conformal prediction can help identify the most suitable uncertainty quantification methods and adapt the predicted confidence intervals to ensure fairness with respect to different attributes.1

Weakly supervised learning aims to reduce the cost of labeling data by using expert-designed labeling rules. However, existing methods require experts to design effective rules in a single shot, which is difficult in the absence of proper guidance and tooling. Therefore, it is still an open question whether experts should spend their limited time writing rules or instead providing instance labels via active learning. In this paper, we investigate how to exploit an expert’s limited time to create effective supervision. First, to develop practical guidelines for rule creation, we conduct an exploratory analysis of diverse collections of existing expert-designed rules and find that rule precision is more important than coverage across datasets. Second, we compare rule creation to individual instance labeling via active learning and demonstrate the importance of both across 6 datasets. Third, we propose an interactive learning framework, INTERVAL, that achieves efficiency by automatically extracting candidate rules based on rich patterns (e.g., by prompting a language model), and effectiveness by soliciting expert feedback on both candidate rules and individual instances. Across 6 datasets, INTERVAL outperforms state-of-the-art weakly supervised approaches by 7% in F1. Furthermore, it requires as few as 10 queries for expert feedback to reach F1 values that existing active learning methods cannot match even with 100 queries.

Self-correction is an approach to improving responses from large language models (LLMs) by refining the responses using LLMs during inference. Prior work has proposed various self-correction frameworks using different sources of feedback, including self-evaluation and external feedback. However, there is still no consensus on the question of when LLMs can correct their own mistakes, as recent studies also report negative results. In this work, we critically survey broad papers and discuss the conditions required for successful self-correction. We first find that prior studies often do not define their research questions in detail and involve impractical frameworks or unfair evaluations that over-evaluate self-correction. To tackle these issues, we categorize research questions in self-correction research and provide a checklist for designing appropriate experiments. Our critical survey based on the newly categorized research questions shows that (1) no prior work demonstrates successful self-correction with feedback from prompted LLMs, except for studies in tasks that are exceptionally suited for self-correction, (2) self-correction works well in tasks that can use reliable external feedback, and (3) large-scale fine-tuning enables self-correction.

Topic taxonomy discovery aims at uncovering topics of different abstraction levels and constructing hierarchical relations between them. Unfortunately, most prior work can hardly model semantic scopes of words and topics by holding the Euclidean embedding space assumption. What’s worse, they infer asymmetric hierarchical relations by symmetric distances between topic embeddings. As a result, existing methods suffer from problems of low-quality topics at high abstraction levels and inaccurate hierarchical relations. To alleviate these problems, this paper develops a Box embedding-based Topic Model (BoxTM) that maps words and topics into the box embedding space, where the asymmetric metric is defined to properly infer hierarchical relations among topics. Additionally, our BoxTM explicitly infers upper-level topics based on correlation between specific topics through recursive clustering on topic boxes. Finally, extensive experiments validate high-quality of the topic taxonomy learned by BoxTM.

Due to the widespread use of large language models (LLMs), we need to understand whether they embed a specific “worldview” and what these views reflect. Recent studies report that, prompted with political questionnaires, LLMs show left-liberal leanings (Feng et al., 2023; Motoki et al., 2024). However, it is as yet unclear whether these leanings are reliable (robust to prompt variations) and whether the leaning is consistent across policies and political leaning. We propose a series of tests which assess the reliability and consistency of LLMs’ stances on political statements based on a dataset of voting-advice questionnaires collected from seven EU countries and annotated for policy issues. We study LLMs ranging in size from 7B to 70B parameters and find that their reliability increases with parameter count. Larger models show overall stronger alignment with left-leaning parties but differ among policy programs: They show a (left-wing) positive stance towards environment protection, social welfare state, and liberal society but also (right-wing) law and order, with no consistent preferences in the areas of foreign policy and migration.