The paper teaches machines to ask clarifying questions by applying NLI.
problem Teaching machines to ask clarifying questions for better comprehension.
method The approach is to use NLI to determine if a clarification question is about a missing piece of information in a post.
result The best model improved precision@1 by 40% and 60% over state-of-the-art baselines.
LLMs are compared to Markov chains for natural language processing.
problem Theoretical analysis of LLMs' generalization capabilities.
method Equivalence between LLMs and Markov chains, studying multi-step inference.
result Derives generalization bounds for LLMs, capturing their behavior in practice.
SCROLLS benchmarks long text NLP tasks, improving existing models.
problem Short NLP benchmarks ignore long texts; SCROLLS addresses this.
method Handpicked long-text datasets for summarization, QA, and inference tasks.
result Improvement potential on SCROLLS tasks, as indicated by initial baselines.
Structured prediction requires searching over a combinatorial number of structures. To tackle it, we introduce SparseMAP: a new method for sparse structured inference, and its natural loss function. SparseMAP automatically selects only a few global structures: it is situated between MAP inference, which picks a single …
Deep learning has improved performance on many natural language processing (NLP) tasks individually. However, general NLP models cannot emerge within a paradigm that focuses on the particularities of a single metric, dataset, and task. We introduce the Natural Language Decathlon (decaNLP), a challenge that spans ten ta…
Many Machine Reading and Natural Language Understanding tasks require reading supporting text in order to answer questions. For example, in Question Answering, the supporting text can be newswire or Wikipedia articles; in Natural Language Inference, premises can be seen as the supporting text and hypotheses as question…
New attack reveals memorization patterns in pre-trained LLMs.
problem Determining if a data point was part of a pre-trained LLM's training set.
method Adapts MIA statistical tests to LLM's perplexity dynamics of subsequences.
result Significantly outperforms prior approaches in membership inference attacks.
We present a memory augmented neural network for natural language understanding: Neural Semantic Encoders. NSE is equipped with a novel memory update rule and has a variable sized encoding memory that evolves over time and maintains the understanding of input sequences through read}, compose and write operations. NSE c…
A method for predicting credal sets in classification tasks using conformal prediction.
problem Designing methods for learning credal set predictors in machine learning.
method Incorporates conformal prediction for predicting credal sets in classification tasks.
result Conformal credal sets are guaranteed to be valid with high probability.
Gaussian processes are conditioned on various types of data.
problem Exact inference in Gaussian processes is limited to linear-Gaussian settings.
method Established an equivalence between GPs and linear diffusion models, allowing for approximate inference in non-linear settings.
result A general-purpose GP inference scheme that handles various conditioning statements, including non-linear physics and natural language.
Deep learning models outperform classical methods in text classification.
problem Improving text classification accuracy using deep learning.
method Comprehensive review of deep learning models and datasets for text classification.
result Deep learning models outperform classical methods on various text classification tasks.
Framework synthesizes programs for simulating complex models and estimating parameters.
problem Parameter estimation for complex models requires manual encoding of fixed model structures.
method Combines LLMs for program synthesis with neural simulation-based inference.
result Identifies plausible model families from open-ended prompts with high accuracy.
In this paper, we propose Dynamic Self-Attention (DSA), a new self-attention mechanism for sentence embedding. We design DSA by modifying dynamic routing in capsule network (Sabouretal.,2017) for natural language processing. DSA attends to informative words with a dynamic weight vector. We achieve new state-of-the-art …
Natural language processing often involves computations with semantic or syntactic graphs to facilitate sophisticated reasoning based on structural relationships. While convolution kernels provide a powerful tool for comparing graph structure based on node (word) level relationships, they are difficult to customize and…
Paper refines cross-lingual word embeddings using Manhattan norm.
problem Sensitivity of ℓ2 norm loss function to outliers in CLWEs. method Post-processing step using ℓ1 norm to improve CLWEs. result The ℓ1 refinement substantially outperforms state-of-the-art baselines. Remasking improves the quality of discrete diffusion models for natural language and image generation.
problem Limited iterative refinement in masked discrete diffusion models.
method Introducing ReMDM sampler that allows remasking during inference.
result Remasking enables better quality outputs with increased sampling steps.
Neural network models have been very successful at achieving high accuracy on natural language inference (NLI) tasks. However, as demonstrated in recent literature, when tested on some simple adversarial examples, most of the models suffer a significant drop in performance. This raises the concern about the robustness …
POUF fine-tunes large models without labeled data.
problem Lack of labeled data for fine-tuning large pre-trained models.
method Prompt-oriented unsupervised fine-tuning.
result Consistent improvements across various tasks.
New method reduces bias in NLI models using ensemble adversarial training.
problem Spurious correlations between hypotheses and entailment classes in NLI datasets.
method Adversarial training with an ensemble of classifiers to reduce bias in sentence representations.
result Ensemble adversarial training produces more robust NLI models, outperforming previous methods.
Large language models have recently achieved state of the art performance across a wide variety of natural language tasks. Meanwhile, the size of these models and their latency have significantly increased, which makes their usage costly, and raises an interesting question: do language models need to be large? We study…
New seq2seq model can copy entire spans, outperforming simpler models in editing tasks.
problem Editing documents or source code using seq2seq models with explicit token copying.
method Extended seq2seq model capable of copying entire input spans to output in one step, new training and inference methods.
result New model consistently outperforms simpler baselines in editing tasks of natural language and source code.
Stan is a probabilistic programming language that is popular in the statistics community, with a high-level syntax for expressing probabilistic models. Stan differs by nature from generative probabilistic programming languages like Church, Anglican, or Pyro. This paper presents a comprehensive compilation scheme to com…
To simultaneously capture syntax and global semantics from a text corpus, we propose a new larger-context recurrent neural network (RNN) based language model, which extracts recurrent hierarchical semantic structure via a dynamic deep topic model to guide natural language generation. Moving beyond a conventional RNN-ba…
Enhances drug discovery models by understanding human language.
problem Low predictive quality of activity prediction models in drug discovery.
method Proposes a novel architecture with separate chemical and natural language input modules and a contrastive pre-training objective.
result Improves predictive performance on few-shot and zero-shot learning benchmarks.
LIDS assesses LLM summaries with interpretable key words.
problem Challenges in evaluating the quality of LLM summaries.
method BERT-SVD-based direction metric and SOFARI for key word extraction.
result LIDS provides interpretable key words for layered themes.
A new approach to rationalization identifies true rationales by considering causal relationships.
problem Existing rationalization methods struggle with spuriousness, where snippets with similar contributions are hard to distinguish.
method The method leverages causal inference to identify non-spurious rationales, defining probabilities of causation based on a structural causal model.
result The proposed causal rationalization outperforms existing methods on real-world datasets.
StatLoRA uses statistical inference to allocate ranks in LoRA fine-tuning, improving performance.
problem Balancing efficiency, expressiveness, and generalization in LoRA rank allocation.
method Formulates LoRA rank allocation as a statistical hypothesis testing problem, using estimated p-values to determine component retention or pruning.
result StatLoRA achieves comparable or better performance than existing methods under matched rank budgets.
A new approach reduces the size of prediction sets in CP, making it more efficient.
problem Large and costly prediction sets in standard CP.
method Expand correctness criterion to include inferred admissible answers, and use prediction cascades to prune implausible labels.
result Empirically effective in natural language processing and drug discovery.
This is a lecture note for the course DS-GA 3001 <Natural Language Understanding with Distributed Representation> at the Center for Data Science , New York University in Fall, 2015. As the name of the course suggests, this lecture note introduces readers to a neural network based approach to natural language understand…
DLM-One speeds up language generation by 500x with continuous models.
problem Efficiently generating text sequences in natural language processing.
method Score-distillation of continuous diffusion language models.
result Achieves up to 500x speedup in inference time with competitive performance.
The paper distills a weighted automaton from RNNs for language modeling.
problem Tackles the gap between deep learning and grammatical inference.
method Uses a spectral approach to infer a weighted automaton from a trained RNN.
result Extracted weighted automata are good approximations of the RNNs, validating the approach.
New analysis shows LLMs don't follow Bayesian inference in ICL.
problem Does in-context learning in LLMs follow Bayesian inference?
method Analyzes ICL through the martingale property, a requirement for Bayesian inference.
result Violations of the martingale property show LLMs don't follow Bayesian inference.
Paper reviews neurolinguistics and language technologies, emphasizing mutual enrichment.
problem Understanding brain activity during language processing.
method Brain imaging studies and natural language representations.
result Development of brain-aware natural language representations.
Describes explaining neurons in deep representations using compositional logical concepts.
problem Interpreting neuron behavior in deep neural networks.
method Identifying compositional logical concepts that closely approximate neuron behavior.
result Compositional explanations provide insights into model performance and allow for adversarial example creation.
LLMs encode latent topic distributions, suggesting Bayesian inference.
problem Capturing topic structure from large language models.
method Connecting LLM optimization to implicit Bayesian inference and de Finetti's theorem.
result LLMs recover latent topic distributions, matching LDA-generated topics.
Study uses simulation-based inference to decode brain activity from synthetic stimuli.
problem Reversing the process of brain activity emulation to recover stimuli or their properties.
method Pairing brain emulator with LLMs to learn a probabilistic mapping from brain maps to stimulus parameters.
result LLMs can serve as controllable stimulus generators and parameters can be recovered from brain maps.
For joint inference over multiple variables, a variety of structured prediction techniques have been developed to model correlations among variables and thereby improve predictions. However, many classical approaches suffer from one of two primary drawbacks: they either lack the ability to model high-order correlations…
Transformers improve logical reasoning on longer proofs but struggle with length.
problem Understanding systematic generalization in neural proof generation.
method Soft theorem-proving using Transformer models, evaluating logical consistency and inference accuracy.
result Transformers improve generalization with longer proofs but have difficulty with length.
Overparameterized transformer networks have obtained state of the art results in various natural language processing tasks, such as machine translation, language modeling, and question answering. These models contain hundreds of millions of parameters, necessitating a large amount of computation and making them prone t…
PixL2R maps natural language to pixel-based rewards for RL, improving sample efficiency.
problem Sparse reward settings in RL limit applicability to complex problems.
method Directly maps natural language descriptions to pixel-based rewards for guiding RL.
result Language-based rewards significantly improve sample efficiency in policy learning.
The task of Natural Language Inference (NLI) is widely modeled as supervised sentence pair classification. While there has been a lot of work recently on generating explanations of the predictions of classifiers on a single piece of text, there have been no attempts to generate explanations of classifiers operating on …
Improved robot navigation using multi-head attention for natural language instructions.
problem Improving robot navigation in unfamiliar environments.
method Proposes a multi-head attention mechanism blending layer in a neural network model.
result Significant performance gains in translating instructions for unseen environments.
LLMs translate natural language trading intents into correct option strategies using a domain-specific language.
problem Challenges in translating natural language trading intents into correct option strategies due to the complexity of option chain data.
method Introduce Option Query Language (OQL) as a domain-specific intermediate representation to abstract option markets into high-level primitives under grammatical rules. Use LLMs as semantic parsers and validate queries by an engine.
result Significantly improves execution accuracy and logical consistency over direct baselines.
BERTino is a lightweight Italian DistilBERT model for NLP tasks.
problem High computational and memory demands of large language models.
method Developed a DistilBERT model tailored for Italian language.
result F1 scores comparable to BERTBASE with significant speed improvements.
Automates translating natural language to Verilog for digital design.
problem Manual translation of natural language specifications to Verilog is time-consuming and error-prone.
method Fine-tuned GPT-2 to derive Verilog from English, using a dataset of design tasks.
result GPT-2 achieved 94.8% correct translation across simple and abstract design tasks.
Inference in log-linear models scales linearly in the size of output space in the worst-case. This is often a bottleneck in natural language processing and computer vision tasks when the output space is feasibly enumerable but very large. We propose a method to perform inference in log-linear models with sublinear amor…
SpanishTinyRoBERTa distills large Spanish models into efficient question-answering models.
problem Efficient Spanish question-answering models for resource-constrained environments.
method Knowledge distillation from large Spanish language models onto a smaller model.
result SpanishTinyRoBERTa achieves comparable performance to large models with faster inference.
Fine-tunes language models with captions for differential equation solving.
problem Overreliance on function data in operator learning.
method Integrates human knowledge through captions and fine-tunes language models.
result Significantly enhanced performance and reduced function data requirements.