Search Results for author:
Found 20 papers, 14 papers with code
DeepTheorem: Advancing LLM Reasoning for Theorem Proving Through Natural Language and Reinforcement Learning
In this work, we propose DeepTheorem, a comprehensive informal theorem-proving framework exploiting natural language to enhance LLM mathematical reasoning.
Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training
Mixture-of-Experts (MoE) architectures within Large Reasoning Models (LRMs) have achieved impressive reasoning capabilities by selectively activating experts to facilitate structured cognitive processes.
Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards
Large Language Models (LLMs) show great promise in complex reasoning, with Reinforcement Learning with Verifiable Rewards (RLVR) being a key enhancement strategy.
DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning
The capacity for complex mathematical reasoning is a key benchmark for artificial intelligence.
Dancing with Critiques: Enhancing LLM Reasoning with Stepwise Natural Language Self-Critique
Traditional inference time scaling methods utilize scalar reward signals from process reward models to evaluate candidate reasoning steps, but these scalar rewards lack the nuanced qualitative information essential for understanding and justifying each step.
The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models
By training exclusively on the initial prefix substrings (as few as 8 tokens), UPFT removes the need for labeled data or exhaustive sampling.
Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs
To address underthinking, we propose a decoding strategy with thought switching penalty TIP that discourages premature transitions between thoughts, encouraging deeper exploration of each reasoning path.
Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs
The remarkable performance of models like the OpenAI o1 can be attributed to their ability to emulate human-like long-time thinking during inference.
Teaching LLMs to Refine with Tools
We propose CaP, a novel approach that uses external tools to refine chain-of-thought (CoT) responses generated by the same or other LLMs.
Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability
Our results underscore the potential of leveraging critical tokens to reduce errors in reasoning tasks, advancing the development of AI systems capable of robust logical deduction.
Draft Model Knows When to Stop: A Self-Verification Length Policy for Speculative Decoding
Speculative Decoding (SD) has become an important technique in accelerating the inference speed of large language models.
Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training
DeRTa incorporates two novel components: (1) Maximum Likelihood Estimation (MLE) with Harmful Response Prefix, which trains models to recognize and avoid unsafe content by appending a segment of harmful response to the beginning of a safe response, and (2) Reinforced Transition Optimization (RTO), which equips models with the ability to transition from potential harm to safety refusal consistently throughout the harmful response sequence.
How Far Are We on the Decision-Making of LLMs? Evaluating LLMs' Gaming Ability in Multi-Agent Environments
Researchers have examined LLMs' decision-making through the lens of Game Theory.
CriticBench: Benchmarking LLMs for Critique-Correct Reasoning
Utilizing CriticBench, we evaluate and dissect the performance of 17 LLMs in generation, critique, and correction reasoning, i. e., GQC reasoning.
Querying as Prompt: Parameter-Efficient Learning for Multimodal Language Model
Its core innovation is a novel modality-bridging method that allows a set of modality-specific queries to be input as soft prompts into a frozen pre-trained language model.
Leveraging Word Guessing Games to Assess the Intelligence of Large Language Models
Ideally, an advanced agent should possess the ability to accurately describe a given word using an aggressive description while concurrently maximizing confusion in the conservative description, enhancing its participation in the game.
Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate
To address the DoT problem, we propose a Multi-Agent Debate (MAD) framework, in which multiple agents express their arguments in the state of "tit for tat" and a judge manages the debate process to obtain a final solution.
Exploring Human-Like Translation Strategy with Large Language Models
Compared to typical machine translation that focuses solely on source-to-target mapping, LLM-based translation can potentially mimic the human translation process which might take preparatory steps to ensure high-quality translation.
ParroT: Translating during Chat using Large Language Models tuned with Human Translation and Feedback
Therefore, we propose ParroT, a framework to enhance and regulate the translation abilities during chat based on open-source LLMs (e. g., LLaMA), human-written translation and feedback data.
AIM 2020 Challenge on Learned Image Signal Processing Pipeline
This paper reviews the second AIM learned ISP challenge and provides the description of the proposed solutions and results.
