Generates biomedical abstracts from titles, years, and keywords.
problem Difficulties in understanding biomedical research papers due to specialized language.
method Conditional transformer-based language model with metadata conditioning.
result Generated abstracts are more relevant and non-trivial than GPT-2.
Large language models can't efficiently reason conditionally in a distribution-free setting.
problem Impossibility of conditional PAC-efficient reasoning in large language models.
method Proof of impossibility in a distribution-free setting for non-atomic input spaces.
result Any algorithm achieving conditional PAC efficiency must defer to the expert model with high probability.
Paper introduces TrufLL for language model training without labeled data.
problem Training language models from scratch with reinforcement learning.
method Dynamic vocabulary truncation in RL for language generation.
result TrufLL successfully learns language generation policies from scratch.
Project aims to improve coherence in language generation models.
problem Models often generate inconsistent text that diverges from the prompt.
method Trained a sentence pair coherence classifier and co-trained GPT-2 with this coherence objective.
result Fine-tuned model generates coherent paragraphs without diverging.
The paper distinguishes between conditional and marginal processes in language models and discusses conditions for usefulness.
problem The conditional nature of language models trained on observed sequences and the need for marginal text-only processes.
method Distinguishing between full conditional language process, marginal text-only process, and model-induced distribution; analyzing assumptions of stationarity and ergodicity.
result The marginal text-only law is useful only when the observed prefix is an approximately sufficient statistic for the latent circumstances relevant to continuation.
Reinforcement learning is a promising framework for solving control problems, but its use in practical situations is hampered by the fact that reward functions are often difficult to engineer. Specifying goals and tasks for autonomous machines, such as robots, is a significant challenge: conventionally, reward function…
The semantic map calibrates uncertainty from language model probabilities.
problem Uncertainty in language model probabilities for professional decisions.
method Prespecified semantic map linking probabilities of verbal responses to probabilities of declared states.
result Language-derived probabilities outperform printed numerical probabilities and recover valid uncertainty coverage.
This paper proposes a new method to connect language and physical actions in reinforcement learning.
problem Connecting linguistic representations to the physical world in embodied agents.
method Language-conditioned goal generators to decouple sensorimotor learning from language acquisition.
result Agents can demonstrate a diversity of behaviors for any given instruction.
MGLM models all possible language channel factorizations for improved multilingual generation.
problem Generating multilingual text with flexibility and quality.
method Generative joint distribution model over language channels, marginalizing all possible factorizations.
result MGLM outperforms traditional models in multilingual generation tasks.
Paper studies model stealing for low-rank language models.
problem Model stealing threatens proprietary models' security and data privacy.
method Theoretical study of model stealing for Hidden Markov Models (HMMs) and low-rank language models using the conditional query model.
result Efficient algorithm for learning any low-rank distribution in the conditional query model.
Multilingual end-to-end (E2E) models have shown great promise in expansion of automatic speech recognition (ASR) coverage of the world's languages. They have shown improvement over monolingual systems, and have simplified training and serving by eliminating language-specific acoustic, pronunciation, and language models…
New approach decouples skill learning and language grounding for autonomous agents.
problem Autonomous acquisition of skills without external instructions and feedback.
method Language-Goal-Behavior (LGB) architecture with semantic representation.
result Decouples skill learning and language grounding, enabling diversity and strategy switching.
Language models are at the heart of numerous works, notably in the text mining and information retrieval communities. These statistical models aim at extracting word distributions, from simple unigram models to recurrent approaches with latent variables that capture subtle dependencies in texts. However, those models a…
Theory predicts neural scaling exponents from language statistics.
problem No existing theory could quantitatively predict neural scaling exponents.
method Isolated two key statistical properties of language.
result Derives a simple formula predicting neural scaling exponents.
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.
This paper investigates how large language models achieve neural collapse, a phenomenon linked to generalization.
problem Neural collapse in large language models under imbalanced and token-rich conditions.
method Empirical investigation of scaling and regularization effects on CLMs' progression towards neural collapse.
result Neural collapse properties develop with scale and regularization, linked to generalization in language modeling.
The study examines how language models learn to represent the world, identifying conditions for ecological veridicality.
problem Understanding when language models learn to represent the world accurately and how this learning process can fail.
method Analyzes the Bayes-optimal next-token cross-entropy decomposition and the role of training ecology in shaping model representations.
result The minimum-complexity zero-excess solution is the quotient partition by training equivalence, and this solution is not preserved in in-context learning or per-task adaptation.
Model detects depression from transcribed interviews using affective language.
problem Detecting depression from transcribed clinical interviews.
method Hierarchical Attention Network with affective conditioning.
result Model achieves state-of-the-art F1 scores in depression detection.
Pre-trained language model boosts RL efficiency.
problem Low sample efficiency in RL, especially in lifelong learning.
method Use a pre-trained task-independent language model for transfer learning.
result Goal-conditional RL agents become more sample efficient.
We address the problem of any-code completion - generating a missing piece of source code in a given program without any restriction on the vocabulary or structure. We introduce a new approach to any-code completion that leverages the strict syntax of programming languages to model a code snippet as a tree - structural…
Language models predict inorganic synthesis conditions and temperatures.
problem Limited data and heuristic approaches constrain inorganic synthesis planning.
method Language models without fine-tuning predict precursor conditions and temperatures.
result Language models achieve high accuracy in predicting synthesis conditions and temperatures.
A new method improves language model extrapolation without changing training.
problem Improving language model performance on sequences not seen during training.
method Perturbation-based training procedure for language models.
result The method consistently improves out-of-support prediction.
Generative Adversarial Networks (GANs) have gathered a lot of attention from the computer vision community, yielding impressive results for image generation. Advances in the adversarial generation of natural language from noise however are not commensurate with the progress made in generating images, and still lag far …
A new sampler for FLMs improves token-level decoding controls.
problem Sampling from FLMs using standard methods collapses marginals and produces invalid sequences.
method Samples clean one-hot endpoints from FLM token marginals and uses Ornstein-Uhlenbeck bridges conditioned on these endpoints.
result The method preserves token-wise posterior-predictive marginals and improves quality-diversity tradeoff.
Recently a variety of LSTM-based conditional language models (LM) have been applied across a range of language generation tasks. In this work we study various model architectures and different ways to represent and aggregate the source information in an end-to-end neural dialogue system framework. A method called snaps…
New method uses low logit rank to simplify complex language models.
problem Understanding and learning from modern language models.
method Exploiting the low logit rank structure of language models for efficient learning.
result An efficient algorithm for learning low logit rank models from queries.
Learned feature representations and sub-phoneme posteriors from Deep Neural Networks (DNNs) have been used separately to produce significant performance gains for speaker and language recognition tasks. In this work we show how these gains are possible using a single DNN for both speaker and language recognition. The u…
Enhanced conformal methods improve validity of LLM outputs.
problem Lack of conditional validity and high false rejection rates in LLM validity guarantees.
method Adaptive conditional conformal procedure and improved scoring function differentiation.
result Demonstrated improved validity and utility on real datasets.
Paper estimates AI hallucinations in conditional generation tasks.
problem Estimating the frequency of AI-generated incorrect responses.
method Developed a method to estimate hallucination probability from generated responses and log probabilities.
result Method accurately estimates hallucination rate in natural language and synthetic tasks.
Combining watermark and non-watermark detectors improves LLM detection.
problem Challenges in detecting watermarked language models due to limited entropy.
method Investigates hybrid schemes combining watermark and non-watermark detectors.
result Hybrid schemes outperform either class of detector under various conditions.
The study analyzes numerical stability in large language models using mixed-precision arithmetic.
problem Numerical stability of large language models using low-precision arithmetic.
method Developed a mixed-precision analysis of transformer inference, deriving bounds for condition numbers and forward error.
result Established that numerical stability is determined by the interplay between weight magnitude and the growth of the residual stream.
It is time-consuming and error-prone to implement inference procedures for each new probabilistic model. Probabilistic programming addresses this problem by allowing a user to specify the model and having a compiler automatically generate an inference procedure for it. For this approach to be practical, it is important…
Reduces gender bias in patient notes while maintaining medical classification accuracy.
problem Bias in natural language processing of patient notes.
method Identifying and removing gendered language using BERT-based classifiers, then augmenting data to maintain performance.
result Minimal degradation in health condition classification tasks with data augmentation.
This paper examines to what degree current deep learning architectures for image caption generation capture spatial language. On the basis of the evaluation of examples of generated captions from the literature we argue that systems capture what objects are in the image data but not where these objects are located: the…
New method samples from LLM posterior for coherent, useful responses.
problem Hallucinations in large language models.
method Posterior sampling for conditional generation, with calibration.
result Achieves statistical guarantees with higher downstream utility.
This work offers a broad perspective on probabilistic modeling and inference in light of recent advances in probabilistic programming, in which models are formally expressed in Turing-complete programming languages. We consider a typical workflow and how probabilistic programming languages can help to automate this wor…
Language models allocate information storage, not collapsing into uniform representations.
problem Incomplete neural collapse in language model representations.
method Analyzing variance and information sharing across 14 models, proving an information floor.
result Within-class variance is allocated information storage, not collapsed into uniform representations.
UQE uses LLMs to analyze unstructured data efficiently.
problem Efficient analytics on unstructured data.
method Proposes UQE, a query engine that uses LLMs to interpret UQL queries.
result Demonstrates efficient analytics on various unstructured data types.
This work introduces RISE to explain LLMs more reliably by distinguishing essential context.
problem Identifying which context elements influence LLM outputs reliably.
method RISE (Redundancy-Insensitive Scoring of Explanation) method.
result RISE provides more robust explanations than traditional methods.
This research explores discrete diffusion models for natural language generation.
problem Challenges in applying diffusion models to discrete data, especially natural language.
method Investigates Discrete Denoising Diffusion Probabilistic Model (D3PM) and compares it with autoregressive models.
result Discrete diffusion models achieve better processing speed than autoregressive models.
ProGen models protein sequences for synthetic biology.
problem Generating proteins without structural annotations.
method Trained a 1.2B-parameter language model on 280M protein sequences.
result ProGen generates proteins with fine-grained control and accuracy.
We introduce a new sampling method for large language models that balances diversity and parallelism.
problem Balancing diversity and parallelism in decoding for large language models.
method Arithmetic sampling framework compatible with various sampling variations.
result Improves estimation of expected BLEU score reward and reduces the gap with beam search.
Linear properties are either universal or absent across language models.
problem Explaining the prevalence of linear properties in language models.
method Proved identifiability of distribution-equivalent next-token predictors and analyzed various notions of linearity.
result Linear properties either hold in all or none distribution-equivalent next-token predictors.
Transformer model for probabilistic dynamical systems.
problem Modeling high-dimensional dynamical systems from noisy observations.
method Parallel between dynamical systems and language modeling; transformer-based model with geometrical properties; iterative training algorithm.
result Fine-grid approximation of conditional probabilities for high-dimensional systems.
Unified framework for ICL in causal and masked models.
problem Understanding ICL in masked language models and comparing it to causal models.
method Developed a statistical learning framework representing context by empirical measure and predicting using context and query.
result Upper bounds for masked and autoregressive objectives under Wasserstein-type regularity conditions.
Two methods improve 10-K item segmentation using large language models.
problem Challenges in extracting specific items from 10-K reports due to variations in document formats and item presentation.
method Two advanced item segmentation methods: GPT4ItemSeg and BERT4ItemSeg.
result BERT4ItemSeg achieves a macro-F1 of 0.9825, surpassing other methods.
Auxiliary Tuning adapts pre-trained models for novel tasks efficiently.
problem Adapting pre-trained models for new tasks efficiently.
method Supplementing pre-trained model with an auxiliary model that shifts output distribution.
result Achieved similar results to training from scratch with fewer resources.
The dominant language models (LMs) such as n-gram and neural network (NN) models represent sentence probabilities in terms of conditionals. In contrast, a new trans-dimensional random field (TRF) LM has been recently introduced to show superior performances, where the whole sentence is modeled as a random field. In thi…