15 citations · 24 across the 20 of their papers we have counts for
22 papers
Decentralized LLM Workflows via Sequential Auctions
Ian Gemp, Shubhendu Trivedi, Adam Fisch +7
We present a scalable framework for solving multi-step tasks through a decentralized market of self-interested agents. Prior theoretical work demonstrated that agents organized thr…
Your Transformer Is Secretly Elastic
Walter Simoncini, Dheeraj Varghese, Gertjan J. Burghouts +1
Scaling up transformers has produced models with broad capabilities, deployed across heterogeneous hardware and fluctuating workloads. Yet, model families offer only a few fixed si…
Pandora's AI Model Routing Box: Efficient Allocation with Costly Value Estimation
Adam Fisch, Shubhendu Trivedi, Fantine Huot +5
Heterogeneous AI systems composed of multiple models, architectures, harnesses, or inference-time settings can improve quality and efficiency by routing queries to the specialist w…
CollabEval: Statistically Efficient Collaborative Model Evaluation via Matrix Completion
Adam Fisch, Daniel Deutsch, Joshua Maynez +5
Evaluating generative AI models is a routine, but resource-intensive, process that is conducted over and over again during the course of model development. In this work, we propose…
Multiple-Prediction-Powered Inference
Charlie Cowen-Breen, Alekh Agarwal, Stephen Bates +4
Statistical estimation often involves tradeoffs between expensive, high-quality measurements and a variety of lower-quality proxies. We introduce Multiple-Prediction-Powered Infere…
MT-PingEval: Evaluating Multi-Turn Collaboration with Private Information Games
Jacob Eisenstein, Fantine Huot, Adam Fisch +2
We present a scalable and verifiable methodology for evaluating language models in multi-turn interactions, using a suite of collaborative games that require effective communicatio…
Learning Steerable Clarification Policies with Collaborative Self-play
Jonathan Berant, Maximillian Chen, Adam Fisch +4
To handle underspecified or ambiguous queries, AI assistants need a policy for managing their uncertainty to determine (a) when to guess the user intent and answer directly, (b) wh…
Plantain: Plan-Answer Interleaved Reasoning
Anthony Liang, Jonathan Berant, Adam Fisch +3
Reasoning models often spend a significant amount of time thinking before they generate a visible response. In the meantime, they do not give the user any hints as to whether their…
Bridging Kolmogorov Complexity and Deep Learning: Asymptotically Optimal Description Length Objectives for Transformers
Peter Shaw, James Cohan, Jacob Eisenstein +1
The Minimum Description Length (MDL) principle offers a formal framework for applying Occam's razor in machine learning. However, its application to neural networks such as Transfo…
Cost-Optimal Active AI Model Evaluation
Anastasios N. Angelopoulos, Jacob Eisenstein, Jonathan Berant +2
The development lifecycle of generative AI systems requires continual evaluation, data acquisition, and annotation, which is costly in both resources and time. In practice, rapid i…
Don't lie to your friends: Learning what you know from collaborative self-play
Jacob Eisenstein, Reza Aghajani, Adam Fisch +5
To be helpful assistants, AI agents must be aware of their own capabilities and limitations. This includes knowing when to answer from parametric knowledge versus using tools, when…
InfAlign: Inference-aware language model alignment
Ananth Balashankar, Ziteng Sun, Jonathan Berant +9
Language model alignment is a critical step in training modern generative language models. Alignment targets to improve win rate of a sample from the aligned model against the base…
Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning
Amrith Setlur, Chirag Nagpal, Adam Fisch +6
A promising approach for improving reasoning in large language models is to use process reward models (PRMs). PRMs provide feedback at each step of a multi-step reasoning trace, po…
ALTA: Compiler-Based Analysis of Transformers
Peter Shaw, James Cohan, Jacob Eisenstein +3
We propose a new programming language called ALTA and a compiler that can map ALTA programs to Transformer weights. ALTA is inspired by RASP, a language proposed by Weiss et al. (2…
Predicting the Target Word of Game-playing Conversations using a Low-Rank Dialect Adapter for Decoder Models
Dipankar Srirag, Aditya Joshi, Jacob Eisenstein
Dialect adapters that improve the performance of LLMs for NLU tasks on certain sociolects/dialects/national varieties ('dialects' for the sake of brevity) have been reported for en…
Robust Preference Optimization through Reward Model Distillation
Adam Fisch, Jacob Eisenstein, Vicky Zayats +5
Language model (LM) post-training (or alignment) involves maximizing a reward function that is derived from preference annotations. Direct Preference Optimization (DPO) is a popula…
Reuse Your Rewards: Reward Model Transfer for Zero-Shot Cross-Lingual Alignment
Zhaofeng Wu, Ananth Balashankar, Yoon Kim +2
Aligning language models (LMs) based on human-annotated preference data is a crucial step in obtaining practical and performant LM-based systems. However, multilingual human prefer…
Transforming and Combining Rewards for Aligning Large Language Models
Zihao Wang, Chirag Nagpal, Jonathan Berant +4
A common approach for aligning language models to human preferences is to first learn a reward model from preference data, and then use this reward model to update the language mod…
Theoretical guarantees on the best-of-n alignment policy
Ahmad Beirami, Alekh Agarwal, Jonathan Berant +4
A simple and effective method for the inference-time alignment and scaling test-time compute of generative models is best-of- sampling, where samples are drawn from a refere…
Out of the Ordinary: Spectrally Adapting Regression for Covariate Shift
Benjamin Eyre, Elliot Creager, David Madras +2
Designing deep neural network classifiers that perform robustly on distributions differing from the available training data is an active area of machine learning research. However,…
Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate Reward Hacking
Jacob Eisenstein, Chirag Nagpal, Alekh Agarwal +9
Reward models play a key role in aligning language model applications towards human preferences. However, this setup creates an incentive for the language model to exploit errors i…
One Vector is Not Enough: Entity-Augmented Distributional Semantics for Discourse Relations
Yangfeng Ji, Jacob Eisenstein
Discourse relations bind smaller linguistic units into coherent texts. However, automatically identifying discourse relations is difficult, because it requires understanding the se…