Search Results for author:
Found 73 papers, 43 papers with code
Can Language Models Solve Olympiad Programming?
In this paper, we introduce the USACO benchmark with 307 problems from the USA Computing Olympiad, along with high-quality unit tests, reference code, and official analyses for each problem.
RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs
A promising approach is reinforcement learning from human feedback (RLHF), which leverages human feedback to update the model in accordance with human preferences and mitigate issues like toxicity and hallucinations.
Language-Guided World Models: A Model-Based Approach to AI Control
Installing probabilistic world models into artificial agents opens an efficient channel for humans to communicate with and control these agents.
QualEval: Qualitative Evaluation for Model Improvement
In this work, we address the shortcomings of quantitative metrics by proposing QualEval, which augments quantitative scalar metrics with automated qualitative evaluation as a vehicle for model improvement.
Progressively Efficient Learning
By equipping a learning agent with an abstract, dynamic language and an intrinsic motivation to learn with minimal communication effort, CEIL leads to emergence of a human-like pattern where the learner and the teacher communicate progressively efficiently by exchanging increasingly more abstract intentions.
SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
We find real-world software engineering to be a rich, sustainable, and challenging testbed for evaluating the next generation of language models.
Ranked #2 on
Bug fixing
on SWE-bench
FireAct: Toward Language Agent Fine-tuning
Recent efforts have augmented language models (LMs) with external tools or environments, leading to the development of language agents that can reason and act.
Ranked #7 on
Question Answering
on Bamboogle
Cognitive Architectures for Language Agents
Recent efforts have augmented large language models (LLMs) with external resources (e. g., the Internet) or internal control flows (e. g., prompt chaining) for tasks requiring grounding or reasoning, leading to a new class of language agents.
Scaling Laws for Imitation Learning in Single-Agent Games
Inspired by recent work in Natural Language Processing (NLP) where "scaling up" has resulted in increasingly more capable LLMs, we investigate whether carefully scaling up model and data size can bring similar improvements in the imitation learning setting for single-agent games.
COLLIE: Systematic Construction of Constrained Text Generation Tasks
Text generation under constraints have seen increasing interests in natural language processing, especially with the rapidly improving capabilities of large language models.
InstructEval: Systematic Evaluation of Instruction Selection Methods
In-context learning (ICL) performs tasks by prompting a large language model (LLM) using an instruction and a small set of annotated examples called demonstrations.
InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback
Our framework is language and platform agnostic, uses self-contained Docker environments to provide safe and reproducible execution, and is compatible out-of-the-box with traditional seq2seq coding methods, while enabling the development of new methods for interactive code generation.
C-STS: Conditional Semantic Textual Similarity
Semantic textual similarity (STS), a cornerstone task in NLP, measures the degree of similarity between a pair of sentences, and has broad application in fields such as information retrieval and natural language understanding.
PruMUX: Augmenting Data Multiplexing with Model Compression
As language models increase in size by the day, methods for efficient inference are critical to leveraging their capabilities for various applications.
Anthropomorphization of AI: Opportunities and Risks
With widespread adoption of AI systems, and the push from stakeholders to make it human-like through alignment techniques, human voice, and pictorial avatars, the tendency for users to anthropomorphize it increases significantly.
Referral Augmentation for Zero-Shot Information Retrieval
We propose Referral-Augmented Retrieval (RAR), a simple technique that concatenates document indices with referrals, i. e. text from other documents that cite or link to the given document, to provide significant performance gains for zero-shot information retrieval.
Tree of Thoughts: Deliberate Problem Solving with Large Language Models
Language models are increasingly being deployed for general problem solving across a wide range of tasks, but are still confined to token-level, left-to-right decision-making processes during inference.
Toxicity in ChatGPT: Analyzing Persona-assigned Language Models
Large language models (LLMs) have shown incredible capabilities and transcended the natural language processing (NLP) community, with adoption throughout many services like healthcare, therapy, education, and customer service.
Reflexion: Language Agents with Verbal Reinforcement Learning
Large language models (LLMs) have been increasingly used to interact with external environments (e. g., games, compilers, APIs) as goal-driven agents.
MUX-PLMs: Data Multiplexing for High-throughput Language Models
The widespread adoption of large language models such as ChatGPT and Bard has led to unprecedented demand for these technologies.
SemSup-XC: Semantic Supervision for Zero and Few-shot Extreme Classification
In this paper, we develop SemSup-XC, a model that achieves state-of-the-art zero-shot and few-shot performance on three XC datasets derived from legal, e-commerce, and Wikipedia data.
Building Scalable Video Understanding Benchmarks through Sports
Our human studies indicate that ASAP can align videos and annotations with high fidelity, precision, and speed.
Controllable Text Generation with Language Constraints
We consider the task of text generation in language models with constraints specified in natural language.
SPARTAN: Sparse Hierarchical Memory for Parameter-Efficient Transformers
Fine-tuning pre-trained language models (PLMs) achieves impressive performance on a range of downstream tasks, and their sizes have consequently been getting bigger.
ALIGN-MLM: Word Embedding Alignment is Crucial for Multilingual Pre-training
In particular, ALIGN-MLM outperforms XLM and MLM by 35 and 30 F1 points on POS-tagging for transfer between languages that differ both in their script and word order (left-to-right v. s.
ReAct: Synergizing Reasoning and Acting in Language Models
While large language models (LLMs) have demonstrated impressive capabilities across tasks in language understanding and interactive decision making, their abilities for reasoning (e. g. chain-of-thought prompting) and acting (e. g. action plan generation) have primarily been studied as separate topics.
WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents
Existing benchmarks for grounding language in interactive environments either lack real-world linguistic elements, or prove difficult to scale up due to substantial human involvement in the collection of data or feedback signals.
Leveraging Language for Accelerated Learning of Tool Manipulation
Robust and generalized tool manipulation requires an understanding of the properties and affordances of different tools.
Using Natural Language and Program Abstractions to Instill Human Inductive Biases in Machines
Co-training on these representations result in more human-like behavior in downstream meta-reinforcement learning agents than less abstract controls (synthetic language descriptions, program induction without learned primitives), suggesting that the abstraction supported by these representations is key.
Can Rationalization Improve Robustness?
Our experiments reveal that the rationale models show the promise to improve robustness, while they struggle in certain scenarios--when the rationalizer is sensitive to positional bias or lexical choices of attack text.
CARETS: A Consistency And Robustness Evaluative Test Suite for VQA
We introduce CARETS, a systematic test suite to measure consistency and robustness of modern VQA models through a series of six fine-grained capability tests.
SemSup: Semantic Supervision for Simple and Scalable Zero-shot Generalization
Prior work along this vein have largely used expensive per-instance annotation or singular class-level descriptions, but per-instance descriptions are hard to scale and single class descriptions may not be rich enough.
DataMUX: Data Multiplexing for Neural Networks
In this paper, we introduce data multiplexing (DataMUX), a technique that enables deep neural networks to process multiple inputs simultaneously using a single compact representation.
Multi-Query Video Retrieval
Retrieving target videos based on text descriptions is a task of great practical value and has received increasing attention over the past few years.
Multi-Stage Episodic Control for Strategic Exploration in Text Games
Text adventure games present unique challenges to reinforcement learning methods due to their combinatorially large action spaces and sparse rewards.
SILG: The Multi-domain Symbolic Interactive Language Grounding Benchmark
We hope SILG enables the community to quickly identify new methodolo- gies for language grounding that generalize to a diverse set of environments and their associated challenges.
When is BERT Multilingual? Isolating Crucial Ingredients for Cross-lingual Transfer
While recent work on multilingual language models has demonstrated their capacity for cross-lingual zero-shot transfer on downstream tasks, there is a lack of consensus in the community as to what shared properties between languages enable such transfer.
SILG: The Multi-environment Symbolic Interactive Language Grounding Benchmark
We hope SILG enables the community to quickly identify new methodologies for language grounding that generalize to a diverse set of environments and their associated challenges.
Revelio: ML-Generated Debugging Queries for Distributed Systems
A major difficulty in debugging distributed systems lies in manually determining which of the many available debugging tools to use and how to query its logs.
Self-Attention Networks Can Process Bounded Hierarchical Languages
Despite their impressive performance in NLP, self-attention networks were recently proved to be limited for processing formal languages with hierarchical structure, such as $\mathsf{Dyck}_k$, the language consisting of well-nested parentheses of $k$ types.
Reading and Acting while Blindfolded: The Need for Semantics in Text Game Agents
Text-based games simulate worlds and interact with players using natural language.
Grounding Language to Entities and Dynamics for Generalization in Reinforcement Learning
We investigate the use of natural language to drive the generalization of control policies and introduce the new multi-task environment Messenger with free-form text manuals describing the environment dynamics.
Multimodal Graph Networks for Compositional Generalization in Visual Question Answering
Compositional generalization is a key challenge in grounding natural language to visual perception.
Connecting Context-specific Adaptation in Humans to Meta-learning
This work connects the context-sensitive nature of cognitive control to a method for meta-learning with context-conditioned adaptation.
Improving Dialog Systems for Negotiation with Personality Modeling
In this paper, we explore the ability to model and infer personality types of opponents, predict their responses, and use this information to adapt a dialog agent's high-level strategy in negotiation tasks.
Safe Reinforcement Learning with Natural Language Constraints
We then develop an agent with a modular architecture that can interpret and adhere to such textual constraints while learning new tasks.
Projection-Based Constrained Policy Optimization
We consider the problem of learning control policies that optimize a reward function while satisfying constraints due to considerations of safety, fairness, or other costs.
Keep CALM and Explore: Language Models for Action Generation in Text-based Games
In this paper, we propose the Contextual Action Language Model (CALM) to generate a compact set of action candidates at each game state.
Guiding Attention for Self-Supervised Learning with Transformers
In this paper, we propose a simple and effective technique to allow for efficient self-supervised learning with bi-directional Transformers.
Learning Rewards from Linguistic Feedback
The sentiment models outperform the inference network, with the "pragmatic" model approaching human performance.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+2
Towards Unique and Informative Captioning of Images
We find that modern captioning systems return higher likelihoods for incorrect distractor sentences compared to ground truth captions, and that evaluation metrics like SPICE can be 'topped' using simple captioning systems relying on object detectors.
Evolving Graphical Planner: Contextual Global Planning for Vision-and-Language Navigation
The ability to perform effective planning is crucial for building an instruction-following agent.
Accelerating Safe Reinforcement Learning with Constraint-mismatched Policies
We consider the problem of reinforcement learning when provided with (1) a baseline control policy and (2) a set of constraints that the learner must satisfy.
Robust and Interpretable Grounding of Spatial References with Relation Networks
Learning representations of spatial references in natural language is a key challenge in tasks like autonomous navigation and robotic manipulation.
Universal Adversarial Attacks with Natural Triggers for Text Classification
Recent work has demonstrated the vulnerability of modern text classifiers to universal adversarial attacks, which are input-agnostic sequences of words added to text processed by classifiers.
Take the Scenic Route: Improving Generalization in Vision-and-Language Navigation
In the Vision-and-Language Navigation (VLN) task, an agent with egocentric vision navigates to a destination given natural language instructions.
A Generalized Algorithm for Multi-Objective Reinforcement Learning and Policy Adaptation
We introduce a new algorithm for multi-objective reinforcement learning (MORL) with linear preferences, with the goal of enabling few-shot adaptation to new tasks.
Multi-Objective Reinforcement Learning
reinforcement-learning
Calibration, Entropy Rates, and Memory in Language Models
Building accurate language models that capture meaningful long-term dependencies is a core challenge in natural language processing.
Task-Agnostic Dynamics Priors for Deep Reinforcement Learning
While model-based deep reinforcement learning (RL) holds great promise for sample efficiency and generalization, learning an accurate dynamics model is often challenging and requires substantial interaction with the environment.
Learning Physics Priors for Deep Reinforcement Learing
While model-based deep reinforcement learning (RL) holds great promise for sample efficiency and generalization, learning an accurate dynamics model is challenging and often requires substantial interactions with the environment.
Improving Language Understanding by Generative Pre-Training
We demonstrate that large gains on these tasks can be realized by generative pre-training of a language model on a diverse corpus of unlabeled text, followed by discriminative fine-tuning on each specific task.
Ranked #3 on
Natural Language Inference
on SciTail
Grounding Language for Transfer in Deep Reinforcement Learning
In this paper, we explore the utilization of natural language to drive transfer for reinforcement learning (RL).
Representation Learning for Grounded Spatial Reasoning
The interpretation of spatial references is highly contextual, requiring joint inference over both language and the environment.
Unsupervised Learning of Morphological Forests
This paper focuses on unsupervised modeling of morphological families, collectively comprising a forest over the language vocabulary.
Neural Generation of Regular Expressions from Natural Language with Minimal Domain Knowledge
This paper explores the task of translating natural language queries into regular expressions which embody their meaning.
sk_p: a neural program corrector for MOOCs
We present a novel technique for automatic program correction in MOOCs, capable of fixing both syntactic and semantic errors without manual, problem specific correction strategies.
Nonparametric Spherical Topic Modeling with Word Embeddings
In this paper, we propose to use the von Mises-Fisher distribution to model the density of words over a unit sphere.
Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning
Most successful information extraction systems operate with access to a large collection of documents.
Language Understanding for Text-based Games Using Deep Reinforcement Learning
We evaluate our approach on two game worlds, comparing against baselines using bag-of-words and bag-of-bigrams for state representations.
An Unsupervised Method for Uncovering Morphological Chains
In contrast, we propose a model for unsupervised morphological analysis that integrates orthographic and semantic views of words.
JUMP-Means: Small-Variance Asymptotics for Markov Jump Processes
We derive the small-variance asymptotics for parametric and nonparametric MJPs for both directly observed and hidden state models.
