Search Results for author:
Found 28 papers, 10 papers with code
Transformers Struggle to Learn to Search
This difficulty is not resolved even as the number of parameters is increased, suggesting that increasing model scale will not lead to robust search abilities.
Self-Generated Critiques Boost Reward Modeling for Language Models
Reward modeling is crucial for aligning large language models (LLMs) with human preferences, especially in reinforcement learning from human feedback (RLHF).
Self-Consistency Preference Optimization
Self-alignment, whereby models learn to improve themselves without human annotation, is a rapidly growing research area.
Self-Taught Evaluators
Model-based evaluation is at the heart of successful model development -- as a reward model for training, and as a replacement for human evaluation.
An Introduction to Vision-Language Modeling
Then, we present and discuss approaches to evaluate VLMs.
Self-Rewarding Language Models
We posit that to achieve superhuman agents, future models require superhuman feedback in order to provide an adequate training signal.
GPQA: A Graduate-Level Google-Proof Q&A Benchmark
We present GPQA, a challenging dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry.
Leveraging Implicit Feedback from Deployment Data in Dialogue
We study improving social conversational agents by learning from natural dialogue between users and a deployed model, without extra annotations.
Testing the General Deductive Reasoning Capacity of Large Language Models Using OOD Examples
Given the intractably large size of the space of proofs, any model that is capable of general deductive reasoning must generalize to proofs of greater complexity.
Extrapolative Controlled Sequence Generation via Iterative Refinement
We study the problem of extrapolative controlled generation, i. e., generating sequences with attribute values beyond the range seen in training.
Reward Gaming in Conditional Text Generation
To align conditional text generation model outputs with desired behaviors, there has been an increasing focus on training the model using reinforcement learning (RL) with reward functions learned from human annotations.
What Do NLP Researchers Believe? Results of the NLP Community Metasurvey
We present the results of the NLP Community Metasurvey.
SQuALITY: Building a Long-Document Summarization Dataset the Hard Way
Summarization datasets are often assembled either by scraping naturally occurring public-domain summaries -- which are nearly always in difficult-to-work-with technical domains -- or by using approximate heuristics to extract them from everyday text -- which frequently yields unfaithful summaries.
Token Dropping for Efficient BERT Pretraining
Transformer-based models generally allocate the same amount of computation for each token in a given sequence.
QuALITY: Question Answering with Long Input Texts, Yes!
To enable building and testing models on long-document comprehension, we introduce QuALITY, a multiple-choice QA dataset with context passages in English that have an average length of about 5, 000 tokens, much longer than typical current models can process.
Amortized Noisy Channel Neural Machine Translation
For all three approaches, the generated translations fail to achieve rewards comparable to BSR, but the translation quality approximated by BLEU and BLEURT is similar to the quality of BSR-produced translations.
AgreeSum: Agreement-Oriented Multi-Document Summarization
Given the lack of existing datasets, we create a dataset for AgreeSum, and provide annotations on article-summary entailment relations for a subset of the clusters in the dataset.
Comparing Test Sets with Item Response Theory
Recent years have seen numerous NLP datasets introduced to evaluate the performance of fine-tuned models on natural language understanding tasks.
Text Generation by Learning from Demonstrations
Current approaches to text generation largely rely on autoregressive models and maximum likelihood estimation.
Intermediate-Task Transfer Learning with Pretrained Language Models: When and Why Does It Work?
However, we fail to observe more granular correlations between probing and target task performance, highlighting the need for further work on broad-coverage probing benchmarks.
ENGINE: Energy-Based Inference Networks for Non-Autoregressive Machine Translation
We propose to train a non-autoregressive machine translation model to minimize the energy defined by a pretrained autoregressive model.
Intermediate-Task Transfer Learning with Pretrained Models for Natural Language Understanding: When and Why Does It Work?
However, we fail to observe more granular correlations between probing and target task performance, highlighting the need for further work on broad-coverage probing benchmarks.
Consistency of a Recurrent Language Model With Respect to Incomplete Decoding
Despite strong performance on a variety of tasks, neural sequence models trained with maximum likelihood have been shown to exhibit issues such as length bias and degenerate repetition.
Improving Joint Training of Inference Networks and Structured Prediction Energy Networks
Deep energy-based models are powerful, but pose challenges for learning and inference (Belanger and McCallum, 2016).
Towards Actual (Not Operational) Textual Style Transfer Auto-Evaluation
Regarding the problem of automatically generating paraphrases with modified styles or attributes, the difficulty lies in the lack of parallel corpora.
The Daunting Task of Real-World Textual Style Transfer Auto-Evaluation
The difficulty of textual style transfer lies in the lack of parallel corpora.
Unsupervised Evaluation Metrics and Learning Criteria for Non-Parallel Textual Transfer
We show that the metric of post-transfer classification accuracy is insufficient on its own, and propose additional metrics based on semantic preservation and fluency as well as a way to combine them into a single overall score.
