565 citations · 614 across the 14 of their papers we have counts for
14 papers
Pre-training under infinite compute
Konwoo Kim, Suhas Kotha, Percy Liang +1
Since compute grows much faster than web text available for language model pre-training, we ask how one should approach pre-training under fixed data and no compute constraints. We…
s1: Simple test-time scaling
Niklas Muennighoff, Zitong Yang, Weijia Shi +7
Test-time scaling is a promising new approach to language modeling that uses extra test-time compute to improve performance. Recently, OpenAI's o1 model showed this capability but…
Eliciting Language Model Behaviors with Investigator Agents
Xiang Lisa Li, Neil Chowdhury, Daniel D. Johnson +4
Language models exhibit complex, diverse behaviors when prompted with free-form text, making it difficult to characterize the space of possible outputs. We study the problem of beh…
Auditing Prompt Caching in Language Model APIs
Chenchen Gu, Xiang Lisa Li, Rohith Kuditipudi +2
Prompt caching in large language models (LLMs) results in data-dependent timing variations: cached prompts are processed faster than non-cached prompts. These timing differences in…
PERSONA: A Reproducible Testbed for Pluralistic Alignment
Louis Castricato, Nathan Lile, Rafael Rafailov +2
The rapid advancement of language models (LMs) necessitates robust alignment with diverse user values. However, current preference optimization approaches often fail to capture the…
AutoBencher: Towards Declarative Benchmark Construction
Xiang Lisa Li, Farzaan Kaiyom, Evan Zheran Liu +3
We present AutoBencher, a declarative framework for automatic benchmark construction, and use it to scalably discover novel insights and vulnerabilities of existing language models…
Learning to (Learn at Test Time): RNNs with Expressive Hidden States
Yu Sun, Xinhao Li, Karan Dalal +9
Self-attention performs well in long context but has quadratic complexity. Existing RNN layers have linear complexity, but their performance in long context is limited by the expre…
Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators
Yann Dubois, Balázs Galambosi, Percy Liang +1
LLM-based auto-annotators have become a key component of the LLM development process due to their cost-effectiveness and scalability compared to human-based evaluation. However, th…
"Sorry, Come Again?" Prompting -- Enhancing Comprehension and Diminishing Hallucination with [PAUSE]-injected Optimal Paraphrasing
Vipula Rawte, S. M Towhidul Islam Tonmoy, S M Mehedi Zaman +4
Hallucination has emerged as the most vulnerable aspect of contemporary Large Language Models (LLMs). In this paper, we introduce the Sorry, Come Again (SCA) prompting, aimed to av…
On the Learnability of Watermarks for Language Models
Chenchen Gu, Xiang Lisa Li, Percy Liang +1
Watermarking of language model outputs enables statistical detection of model-generated text, which can mitigate harms and misuses of language models. Existing watermarking strateg…
Benchmarking Multi-Domain Active Learning on Image Classification
Jiayi Li, Rohan Taori, Tatsunori B. Hashimoto
Active learning aims to enhance model performance by strategically labeling informative data points. While extensively studied, its effectiveness on large-scale, real-world dataset…
Benchmarking and Improving Generator-Validator Consistency of Language Models
Xiang Lisa Li, Vaishnavi Shrivastava, Siyan Li +2
As of September 2023, ChatGPT correctly answers "what is 7+8" with 15, but when asked "7+8=15, True or False" it responds with "False". This inconsistency between generating and va…
Learning to (Learn at Test Time)
Yu Sun, Xinhao Li, Karan Dalal +6
We reformulate the problem of supervised learning as learning to learn with two nested loops (i.e. learning problems). The inner loop learns on each individual instance with self-s…
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
Aarohi Srivastava, Abhinav Rastogi, Abhishek Rao +448
Language models demonstrate both quantitative improvement and new qualitative capabilities with increasing scale. Despite their potentially transformative impact, these new capabil…