27 citations · 122 across the 14 of their papers we have counts for
16 papers
OpenAI GPT-5 System Card
Aaditya Singh, Adam Fry, Adam Perelman +483
This is the system card published alongside the OpenAI GPT-5 launch, August 2025. GPT-5 is a unified system with a smart and fast model that answers most questions, a deeper reason…
Training LLMs for Honesty via Confessions
Manas Joglekar, Jeremy Chen, Gabriel Wu +4
Large language models (LLMs) can be dishonest when reporting on their actions and beliefs -- for example, they may overstate their confidence in factual claims or cover up evidence…
Deliberative Alignment: Reasoning Enables Safer Language Models
Melody Y. Guan, Manas Joglekar, Eric Wallace +12
As large-scale language models increasingly impact safety-critical domains, ensuring their reliable adherence to well-defined principles remains a fundamental challenge. We introdu…
Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision
Collin Burns, Pavel Izmailov, Jan Hendrik Kirchner +9
Widely used alignment techniques, such as reinforcement learning from human feedback (RLHF), rely on the ability of humans to supervise model behavior - for example, to evaluate wh…
Neural Input Search for Large Scale Recommendation Models
Manas R. Joglekar, Cong Li, Jay K. Adams +2
Recommendation problems with large numbers of discrete items, such as products, webpages, or videos, are ubiquitous in the technology industry. Deep neural networks are being incre…
Distributed Evaluation of Subgraph Queries Using Worstcase Optimal LowMemory Dataflows
Khaled Ammar, Frank McSherry, Semih Salihoglu +1
We study the problem of finding and monitoring fixed-size subgraphs in a continually changing large-scale graph. We present the first approach that (i) performs worst-case optimal…
SLiMFast: Guaranteed Results for Data Fusion and Source Reliability
Manas Joglekar, Theodoros Rekatsinas, Hector Garcia-Molina +2
We focus on data fusion, i.e., the problem of unifying conflicting data from data sources into a single representation by estimating the source accuracies. We propose SLiMFast, a f…
Aggregations over Generalized Hypertree Decompositions
Manas Joglekar, Rohan Puttagunta, Christopher Ré
We study a class of aggregate-join queries with multiple aggregation operators evaluated over annotated relations. We show that straightforward extensions of standard multiway join…
It's all a matter of degree: Using degree information to optimize multiway joins
Manas Joglekar, Christopher Re
We optimize multiway equijoins on relational tables using degree information. We give a new bound that uses degree information to more tightly bound the maximum output size of a qu…
Interactive Data Exploration with Smart Drill-Down
Manas Joglekar, Hector Garcia-Molina, Aditya Parameswaran
We present {\em smart drill-down}, an operator for interactively exploring a relational table to discover and summarize "interesting" groups of tuples. Each group of tuples is desc…
Evaluating the Crowd with Confidence
Manas Joglekar, Hector Garcia-Molina, Aditya Parameswaran
Worker quality control is a crucial aspect of crowdsourcing systems; typically occupying a large fraction of the time and money invested on crowdsourcing. In this work, we devise t…
Comprehensive and Reliable Crowd Assessment Algorithms
Manas Joglekar, Hector Garcia-Molina, Aditya Parameswaran
Evaluating workers is a critical aspect of any crowdsourcing system. In this paper, we devise techniques for evaluating workers by finding confidence intervals on their error rates…
Exploiting Correlations for Expensive Predicate Evaluation
Manas Joglekar, Hector Garcia-Molina, Aditya Parameswaran +1
User Defined Function(UDFs) are used increasingly to augment query languages with extra, application dependent functionality. Selection queries involving UDF predicates tend to be…
GYM: A Multiround Join Algorithm In MapReduce
Foto Afrati, Manas Joglekar, Christopher Ré +2
Multiround algorithms are now commonly used in distributed data processing systems, yet the extent to which algorithms can benefit from running more rounds is not well understood.…
Average Case Analysis of the Classical Algorithm for Markov Decision Processes with Büchi Objectives
Krishnendu Chatterjee, Manas Joglekar, Nisarg Shah
We consider Markov decision processes (MDPs) with -regular specifications given as parity objectives. We consider the problem of computing the set of almost-sure winning vertice…
Symbolic Algorithms for Qualitative Analysis of Markov Decision Processes with Büchi Objectives
Krishnendu Chatterjee, Monika Henzinger, Manas Joglekar +1
We consider Markov decision processes (MDPs) with ω-regular specifications given as parity objectives. We consider the problem of computing the set of almost-sure winning states fr…