Number of papers: 6
- Authors: Yang, John and Prabhakar, Akshara and Yao, Shunyu and Pei, Kexin and Narasimhan, Karthik R
- Abstract: Amidst the advent of language models (LMs) and their wide-ranging capabilities, concerns have been raised about their implications with regards to privacy and security. In particular, the emergence of language agents as a promising aid for automating and augmenting digital work poses immediate questions concerning their misuse as malicious cybersecurity actors. With their exceptional compute efficiency and execution speed relative to human counterparts, language agents may be extremely adept at ...
- Link: Read Paper
- Labels: program testing, vulnerability exploitation, benchmark
- Authors: Yang, Kaiyu and Swope, Aidan and Gu, Alex and Chalamala, Rahul and Song, Peiyang and Yu, Shixing and Godil, Saad and Prenger, Ryan J and Anandkumar, Animashree
- Abstract: Large language models (LLMs) have shown promise in proving formal theorems using proof assistants such as Lean. However, existing methods are difficult to reproduce or build on, due to private code, data, and large compute requirements. This has created substantial barriers to research on machine learning methods for theorem proving. This paper removes these barriers by introducing LeanDojo: an open-source Lean playground consisting of toolkits, data, models, and benchmarks. LeanDojo extracts da...
- Link: Read Paper
- Labels: prompt strategy, retrieval-augmented generation
- Authors: Shinn, Noah and Cassano, Federico and Gopinath, Ashwin and Narasimhan, Karthik and Yao, Shunyu
- Abstract: Large language models (LLMs) have been increasingly used to interact with external environments (e.g., games, compilers, APIs) as goal-driven agents. However, it remains challenging for these language agents to quickly and efficiently learn from trial-and-error as traditional reinforcement learning methods require extensive training samples and expensive model fine-tuning. We propose Reflexion, a novel framework to reinforce language agents not by updating weights, but instead through linguistic...
- Link: Read Paper
- Labels: hallucination in reasoning, prompt strategy
- Authors: Ye, Xi and Chen, Qiaochu and Dillig, Isil and Durrett, Greg
- Abstract: Prior work has combined chain-of-thought prompting in large language models (LLMs) with programmatic representations to perform effective and transparent reasoning. While such an approach works well for tasks that only require forward reasoning (e.g., straightforward arithmetic), it is less effective for constraint solving problems that require more sophisticated planning and search. In this paper, we propose a new satisfiability-aided language modeling (SatLM) approach for improving the reasoni...
- Link: Read Paper
- Labels: hallucination in reasoning, prompt strategy
- Authors: Xie, Yuxi and Kawaguchi, Kenji and Zhao, Yiran and Zhao, James Xu and Kan, Min-Yen and He, Junxian and Xie, Michael
- Abstract: Breaking down a problem into intermediate steps has demonstrated impressive performance in Large Language Model (LLM) reasoning. However, the growth of the reasoning chain introduces uncertainty and error accumulation, making it challenging to elicit accurate final results. To tackle this challenge of uncertainty in multi-step reasoning, we introduce a stepwise self-evaluation mechanism to guide and calibrate the reasoning process of LLMs. We propose a decoding algorithm integrating the self-eva...
- Link: Read Paper
- Labels: hallucination in reasoning, prompt strategy
- Authors: Yao, Shunyu and Yu, Dian and Zhao, Jeffrey and Shafran, Izhak and Griffiths, Tom and Cao, Yuan and Narasimhan, Karthik
- Abstract: 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. This means they can fall short in tasks that require exploration, strategic lookahead, or where initial decisions play a pivotal role. To surmount these challenges, we introduce a new framework for language model inference, “Tree of Thoughts” (ToT), which generalizes over the popular “Chain of T...
- Link: Read Paper
- Labels: hallucination in reasoning, prompt strategy