Search Results for author:
Found 17 papers, 11 papers with code
Is the Reversal Curse a Binding Problem? Uncovering Limitations of Transformers from a Basic Generalization Failure
Despite their impressive capabilities, LLMs exhibit a basic generalization failure known as the Reversal Curse, where they struggle to learn reversible factual associations.
ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery
To this end, we present ScienceAgentBench, a new benchmark for evaluating language agents for data-driven scientific discovery.
Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization
The levels of generalization also vary across reasoning types: when faced with out-of-distribution examples, transformers fail to systematically generalize for composition but succeed for comparison.
Beamforming Design for Double-Active-RIS-aided Communication Systems with Inter-Excitation
Furthermore, the results demonstrate that the proposed scheme can enhance the WSR by 30\% compared to scenarios that do not take this effect into account when the maximum amplification gain is 40 dB.
LLMs in the Imaginarium: Tool Learning through Simulated Trial and Error
We find that existing LLMs, including GPT-4 and open-source LLMs specifically fine-tuned for tool use, only reach a correctness rate in the range of 30% to 60%, far from reliable use in practice.
Reconfigurable Intelligent Surface-Aided Dual-Function Radar and Communication Systems With MU-MIMO Communication
In this paper, we investigate an reconfigurable intelligent surface (RIS)-aided integrated sensing and communication (ISAC) system.
Joint Beamforming Design for Double Active RIS-assisted Radar-Communication Coexistence Systems
However, when radar and communication equipment coexist in the same system, i. e. radar-communication coexistence (RCC), the interference from communication systems to radar can be large and cannot be ignored.
Secure Wireless Communication in Active RIS-Assisted DFRC System
This work considers a dual-functional radar and communication (DFRC) system with an active reconfigurable intelligent surface (RIS) and a potential eavesdropper.
Mind2Web: Towards a Generalist Agent for the Web
We introduce Mind2Web, the first dataset for developing and evaluating generalist agents for the web that can follow language instructions to complete complex tasks on any website.
Can ChatGPT Defend its Belief in Truth? Evaluating LLM Reasoning via Debate
Large language models (LLMs) such as ChatGPT and GPT-4 have shown impressive performance in complex reasoning tasks.
Automatic Evaluation of Attribution by Large Language Models
We manually curate a set of test examples covering 12 domains from a generative search engine, New Bing.
Scalable Learning with Incremental Probabilistic PCA
Incremental class learning is the classification problem of learning a model where instances from new object classes are added sequentially, and it is desired that the model be retrained only on the new classes with minimal training on the old classes.
Ranked #1 on
Class Incremental Learning
on CIFAR-100 - 50 classes + 10 steps of 5 classes
(using extra training data)
Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters
Chain-of-Thought (CoT) prompting can dramatically improve the multi-step reasoning abilities of large language models (LLMs).
A Retrieve-and-Read Framework for Knowledge Graph Link Prediction
To address the limitations of existing KG link prediction frameworks, we propose a novel retrieve-and-read framework, which first retrieves a relevant subgraph context for the query and then jointly reasons over the context and the query with a high-capacity reader.
Ranked #2 on
Link Prediction
on FB15k-237
Iteratively Prompt Pre-trained Language Models for Chain of Thought
While Pre-trained Language Models (PLMs) internalize a great amount of world knowledge, they have been shown incapable of recalling these knowledge to solve tasks requiring complex & multi-step reasoning.
Automatic Loss Function Search for Predict-Then-Optimize Problems with Strong Ranking Property
Combinatorial optimization problems with parameters to be predicted from side information are commonly seen in a variety of problems during the paradigm shift from reactive decision making to proactive decision making.
