activity
20122024
most citedAsk the Right Questions: Active Question Reformulation with Reinforcement Learning

132 citations · 262 across the 12 of their papers we have counts for

collaborators

14 papers

cs.CL2024★ 4 cited

How Susceptible are LLMs to Influence in Prompts?

Sotiris Anagnostidis, Jannis Bulian

Large Language Models (LLMs) are highly sensitive to prompts, including additional context provided therein. As LLMs grow in capability, understanding their prompt-sensitivity beco…

cs.LG2024★ 6 cited

On scalable oversight with weak LLMs judging strong LLMs

Zachary Kenton, Noah Y. Siegel, János Kramár +8

Scalable oversight protocols aim to enable humans to accurately supervise superhuman AI. In this paper we study debate, where two AI's compete to convince a judge; consultancy, whe…

cs.CL2023★ 18 cited

Assessing Large Language Models on Climate Information

Jannis Bulian, Mike S. Schäfer, Afra Amini +8

As Large Language Models (LLMs) rise in popularity, it is necessary to assess their capability in critically relevant domains. We present a comprehensive evaluation framework, grou…

cs.LG2022★ 48 cited

Scaling Up Models and Data with and

Adam Roberts, Hyung Won Chung, Anselm Levskaya +40

Recent neural network-based language models have benefited greatly from scaling up the size of training datasets and the number of parameters in the models themselves. Scaling can…

cs.CL2022★ 3 cited

Tomayto, Tomahto. Beyond Token-level Answer Equivalence for Question Answering Evaluation

Jannis Bulian, Christian Buck, Wojciech Gajewski +2

The predictions of question answering (QA)systems are typically evaluated against manually annotated finite sets of one or more answers. This leads to a coverage limitation that re…

cs.CL2021

Fool Me Twice: Entailment from Wikipedia Gamification

Julian Martin Eisenschlos, Bhuwan Dhingra, Jannis Bulian +2

We release FoolMeTwice (FM2 for short), a large dataset of challenging entailment pairs collected through a fun multi-player game. Gamification encourages adversarial examples, dra…

cs.CL2021★ 24 cited

CLIMATE-FEVER: A Dataset for Verification of Real-World Climate Claims

Thomas Diggelmann, Jordan Boyd-Graber, Jannis Bulian +2

We introduce CLIMATE-FEVER, a new publicly available dataset for verification of climate change-related claims. By providing a dataset for the research community, we aim to facilit…

cs.CL2019★ 1 cited

Meta Answering for Machine Reading

Benjamin Borschinger, Jordan Boyd-Graber, Christian Buck +7

We investigate a framework for machine reading, inspired by real world information-seeking problems, where a meta question answering system interacts with a black box environment.…

cs.LG2018★ 8 cited

Learning to Coordinate Multiple Reinforcement Learning Agents for Diverse Query Reformulation

Rodrigo Nogueira, Jannis Bulian, Massimiliano Ciaramita

We propose a method to efficiently learn diverse strategies in reinforcement learning for query reformulation in the tasks of document retrieval and question answering. In the prop…

cs.CL2018★ 3 cited

Analyzing Language Learned by an Active Question Answering Agent

Christian Buck, Jannis Bulian, Massimiliano Ciaramita +4

We analyze the language learned by an agent trained with reinforcement learning as a component of the ActiveQA system [Buck et al., 2017]. In ActiveQA, question answering is framed…

cs.CL2017★ 132 cited

Ask the Right Questions: Active Question Reformulation with Reinforcement Learning

Christian Buck, Jannis Bulian, Massimiliano Ciaramita +4

We frame Question Answering (QA) as a Reinforcement Learning task, an approach that we call Active Question Answering. We propose an agent that sits between the user and a black bo…

cs.DS2015

Fixed-parameter Tractable Distances to Sparse Graph Classes

Jannis Bulian, Anuj Dawar

We show that for various classes C of sparse graphs, and several measures of distance to such classes (such as edit distance and elimination distance), the problem of determining t…

cs.DS2014

Graph Isomorphism Parameterized by Elimination Distance to Bounded Degree

Jannis Bulian, Anuj Dawar

A commonly studied means of parameterizing graph problems is the deletion distance from triviality (Guo et al. 2004), which counts vertices that need to be deleted from a graph to…

math.LO2012★ 15 cited

Bare canonicity of representable cylindric and polyadic algebras

Jannis Bulian, Ian Hodkinson

We show that for finite n at least 3, every first-order axiomatisation of the varieties of representable n-dimensional cylindric algebras, diagonal-free cylindric algebras, polyadi…