8 citations · 15 across the 18 of their papers we have counts for
22 papers
Test-Time Adaptation of Reasoning Strategies with Bayesian Nonparametric Memory
Keshav Ramji, Tahira Naseem, Ramón Fernandez Astudillo
While modern large language models (LLMs) have been trained to reason through verbalized chains-of-thought, the generation cost grows substantially due to suboptimal paths to reach…
Learning to Predict Distributions over Weight Updates for Test-Time Adaptation
Azal Ahmad Khan, Keshav Ramji, Tahira Naseem +2
Hypernetworks have recently shown success in dynamically adapting the parameters of Large Language Models (LLMs) at runtime based on signals such as task descriptions or additional…
BOReFT: Manifold Steering of Language Models for Black-box Optimization
Dhruv Agarwal, Rico Angell, Kavitha Srinivas +4
Language models are increasingly used as proposal models for black-box search, from program optimization to molecular design. Existing approaches typically improve proposals throug…
A Continuous-Time Markov Chain Framework for Insertion Language Models
Dhruvesh Patel, Benjamin Rozonoyer, Soumitra Das +3
Insertion Language Models (ILMs) offer several advantages over left-to-right generation and mask-based generation. However, existing formulations of insertion-based generation have…
Thinking Without Words: Efficient Latent Reasoning with Abstract Chain-of-Thought
Keshav Ramji, Tahira Naseem, Ramón Fernandez Astudillo
While long, explicit chains-of-thought (CoT) have proven effective on complex reasoning tasks, they are costly to generate during inference. Non-verbal reasoning methods have emerg…
Insertion Based Sequence Generation with Learnable Order Dynamics
Dhruvesh Patel, Benjamin Rozonoyer, Gaurav Pandey +3
Existing insertion-based masked diffusion models that generate sequences by interleaving token insertion with unmasking use fixed schedules that are not dependent on the data. For…
Optimal Policy Minimum Bayesian Risk
Ramón Fernandez Astudillo, Md Arafat Sultan, Aashka Trivedi +4
Inference scaling helps LLMs solve complex reasoning problems through extended runtime computation. On top of long chain-of-thought (long-CoT) models, purely inference-time techniq…
Latent Principle Discovery for Language Model Self-Improvement
Keshav Ramji, Tahira Naseem, Ramón Fernandez Astudillo
When language model (LM) users aim to improve the quality of its generations, it is crucial to specify concrete behavioral attributes that the model should strive to reflect. Howev…
Insertion Language Models: Sequence Generation with Arbitrary-Position Insertions
Dhruvesh Patel, Aishwarya Sahoo, Avinash Amballa +3
Autoregressive models (ARMs), which predict subsequent tokens one-by-one ``from left to right,'' have achieved significant success across a wide range of sequence generation tasks.…
Self-Refinement of Language Models from External Proxy Metrics Feedback
Keshav Ramji, Young-Suk Lee, Ramón Fernandez Astudillo +5
It is often desirable for Large Language Models (LLMs) to capture multiple objectives when providing a response. In document-grounded response generation, for example, agent respon…
BRAIn: Bayesian Reward-conditioned Amortized Inference for natural language generation from feedback
Gaurav Pandey, Yatin Nandwani, Tahira Naseem +6
Distribution matching methods for language model alignment such as Generation with Distributional Control (GDC) and Distributional Policy Gradient (DPG) have not received the same…
Scalable Learning of Latent Language Structure With Logical Offline Cycle Consistency
Maxwell Crouse, Ramon Astudillo, Tahira Naseem +4
We introduce Logical Offline Cycle Consistency Optimization (LOCCO), a scalable, semi-supervised method for training a neural semantic parser. Conceptually, LOCCO can be viewed as…
Slide, Constrain, Parse, Repeat: Synchronous SlidingWindows for Document AMR Parsing
Sadhana Kumaravel, Tahira Naseem, Ramon Fernandez Astudillo +2
The sliding window approach provides an elegant way to handle contexts of sizes larger than the Transformer's input window, for tasks like language modeling. Here we extend this ap…
Laziness Is a Virtue When It Comes to Compositionality in Neural Semantic Parsing
Maxwell Crouse, Pavan Kapanipathi, Subhajit Chaudhury +4
Nearly all general-purpose neural semantic parsers generate logical forms in a strictly top-down autoregressive fashion. Though such systems have achieved impressive results across…
AMR Parsing with Instruction Fine-tuned Pre-trained Language Models
Young-Suk Lee, Ramón Fernandez Astudillo, Radu Florian +2
Instruction fine-tuned language models on a collection of instruction annotated datasets (FLAN) have shown highly effective to improve model performance and generalization to unsee…
Inducing and Using Alignments for Transition-based AMR Parsing
Andrew Drozdov, Jiawei Zhou, Radu Florian +4
Transition-based parsers for Abstract Meaning Representation (AMR) rely on node-to-word alignments. These alignments are learned separately from parser training and require a compl…
CBR-iKB: A Case-Based Reasoning Approach for Question Answering over Incomplete Knowledge Bases
Dung Thai, Srinivas Ravishankar, Ibrahim Abdelaziz +7
Knowledge bases (KBs) are often incomplete and constantly changing in practice. Yet, in many question answering applications coupled with knowledge bases, the sparse nature of KBs…
DocAMR: Multi-Sentence AMR Representation and Evaluation
Tahira Naseem, Austin Blodgett, Sadhana Kumaravel +7
Despite extensive research on parsing of English sentences into Abstraction Meaning Representation (AMR) graphs, which are compared to gold graphs via the Smatch metric, full-docum…
Learning to Transpile AMR into SPARQL
Mihaela Bornea, Ramon Fernandez Astudillo, Tahira Naseem +5
We propose a transition-based system to transpile Abstract Meaning Representation (AMR) into SPARQL for Knowledge Base Question Answering (KBQA). This allows us to delegate part of…
Maximum Bayes Smatch Ensemble Distillation for AMR Parsing
Young-Suk Lee, Ramon Fernandez Astudillo, Thanh Lam Hoang +3
AMR parsing has experienced an unprecendented increase in performance in the last three years, due to a mixture of effects including architecture improvements and transfer learning…
A Two-Stage Approach towards Generalization in Knowledge Base Question Answering
Srinivas Ravishankar, June Thai, Ibrahim Abdelaziz +5
Most existing approaches for Knowledge Base Question Answering (KBQA) focus on a specific underlying knowledge base either because of inherent assumptions in the approach, or becau…
Structural Guidance for Transformer Language Models
Peng Qian, Tahira Naseem, Roger Levy +1
Transformer-based language models pre-trained on large amounts of text data have proven remarkably successful in learning generic transferable linguistic representations. Here we s…