Balancing Exploration and Exploitation in LLM using Soft RLLF for
Enhanced Negation Understanding
- URL: http://arxiv.org/abs/2403.01185v1
- Date: Sat, 2 Mar 2024 11:54:55 GMT
- Title: Balancing Exploration and Exploitation in LLM using Soft RLLF for
Enhanced Negation Understanding
- Authors: Ha-Thanh Nguyen, Ken Satoh
- Abstract summary: Finetuning approaches in NLP often focus on exploitation rather than exploration, which may lead to suboptimal models.
We leverage Reinforcement Learning from Logical Feedback to create an effective balance between exploration and exploitation in language models.
This has implications for the development of more accurate, reliable, and logically consistent language models in high-stakes domains.
- Score: 4.799288023353623
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Finetuning approaches in NLP often focus on exploitation rather than
exploration, which may lead to suboptimal models. Given the vast search space
of natural language, this limited exploration can restrict their performance in
complex, high-stakes domains, where accurate negation understanding and logical
reasoning abilities are crucial. To address this issue, we leverage
Reinforcement Learning from Logical Feedback (RLLF) to create an effective
balance between exploration and exploitation in LLMs. Our approach employs an
appropriate benchmark dataset for training and evaluation, highlighting the
importance of exploration in enhancing negation understanding capabilities. We
compare the performance of our RLLF-enhanced LLMs with baseline models trained
without RLLF, demonstrating the value of this balanced approach. Furthermore,
we showcase the potential of our method in legal AI applications by employing
transfer learning and evaluating its impact on negation understanding. Our
experimental results exhibit the effectiveness of balancing exploration and
exploitation with RLLF in improving LLMs' negation capabilities. This has
implications for the development of more accurate, reliable, and logically
consistent language models in high-stakes domains.
Related papers
- RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization [86.30192066451256]
We propose RL-PLUS, a novel hybrid-policy optimization approach for Large Language Models (LLMs)<n> RL-PLUS synergizes internal exploitation with external data to achieve stronger reasoning capabilities and surpass the boundaries of base models.<n>We provide both theoretical analysis and extensive experiments to demonstrate the superiority and generalizability of our approach.
arXiv Detail & Related papers (2025-07-31T23:55:29Z) - Agentic Reinforced Policy Optimization [66.96989268893932]
Large-scale reinforcement learning with verifiable rewards (RLVR) has demonstrated its effectiveness in harnessing the potential of large language models (LLMs) for single-turn reasoning tasks.<n>Current RL algorithms inadequately balance the models' intrinsic long-horizon reasoning capabilities and their proficiency in multi-turn tool interactions.<n>We propose Agentic Reinforced Policy Optimization (ARPO), a novel agentic RL algorithm tailored for training multi-turn LLM-based agents.
arXiv Detail & Related papers (2025-07-26T07:53:11Z) - Improving LLM Reasoning for Vulnerability Detection via Group Relative Policy Optimization [45.799380822683034]
We present an extensive study aimed at advancing RL-based finetuning techniques for Large Language Models (LLMs)<n>We highlight key limitations of commonly adopted LLMs, such as their tendency to over-predict certain types of vulnerabilities while failing to detect others.<n>To address this challenge, we explore the use of Group Relative Policy Optimization (GRPO), a recent policy-gradient method, for guiding LLM behavior through structured, rule-based rewards.
arXiv Detail & Related papers (2025-07-03T11:52:45Z) - Reasoning with Exploration: An Entropy Perspective on Reinforcement Learning for LLMs [112.40801692473723]
Balancing exploration and exploitation is a central goal in reinforcement learning (RL)<n>We introduce a minimal modification to standard RL with only one line of code: augmenting the advantage function with an entropy-based term.<n>Our method achieves significant gains on the Pass@K metric, even when evaluated with extremely large K values.
arXiv Detail & Related papers (2025-06-17T17:54:03Z) - Bridging Supervised Learning and Reinforcement Learning in Math Reasoning [55.889740979706815]
Reinforcement Learning (RL) has played a central role in the recent surge of math abilities by enabling self-improvement through binary verifier signals.<n>In this work, we propose Negative-aware Fine-Tuning (NFT) -- a supervised approach that enables LLMs to reflect on their failures and improve autonomously with no external teachers.
arXiv Detail & Related papers (2025-05-23T17:17:40Z) - OpenVLThinker: An Early Exploration to Complex Vision-Language Reasoning via Iterative Self-Improvement [91.88062410741833]
This study investigates whether similar reasoning capabilities can be successfully integrated into large vision-language models (LVLMs)
We consider an approach that iteratively leverages supervised fine-tuning (SFT) on lightweight training data and Reinforcement Learning (RL) to further improve model generalization.
OpenVLThinker, a LVLM exhibiting consistently improved reasoning performance on challenging benchmarks such as MathVista, MathVerse, and MathVision, demonstrates the potential of our strategy for robust vision-language reasoning.
arXiv Detail & Related papers (2025-03-21T17:52:43Z) - R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning [87.30285670315334]
textbfR1-Searcher is a novel two-stage outcome-based RL approach designed to enhance the search capabilities of Large Language Models.
Our framework relies exclusively on RL, without requiring process rewards or distillation for a cold start.
Our experiments demonstrate that our method significantly outperforms previous strong RAG methods, even when compared to the closed-source GPT-4o-mini.
arXiv Detail & Related papers (2025-03-07T17:14:44Z) - LUNAR: LLM Unlearning via Neural Activation Redirection [20.60687563657169]
Large Language Models (LLMs) benefit from training on ever larger amounts of textual data, but they increasingly incur the risk of leaking private information.
We propose LUNAR, a novel unlearning methodology grounded in the Linear Representation Hypothesis.
We show that LUNAR achieves state-of-the-art unlearning performance while significantly enhancing the controllability of the unlearned model during inference.
arXiv Detail & Related papers (2025-02-11T03:23:22Z) - Reinforcement Learning for Aligning Large Language Models Agents with Interactive Environments: Quantifying and Mitigating Prompt Overfitting [40.78026627009521]
Reinforcement learning (RL) is a promising approach for aligning large language models (LLMs) knowledge with sequential decision-making tasks.
We propose a novel framework to analyze the sensitivity of LLMs to prompt formulations following RL training in a textual environment.
arXiv Detail & Related papers (2024-10-25T18:25:35Z) - Insights from the Inverse: Reconstructing LLM Training Goals Through Inverse RL [7.988692259455583]
Large language models (LLMs) trained with Reinforcement Learning from Human Feedback have demonstrated remarkable capabilities, but their underlying reward functions and decision-making processes remain opaque.
This paper introduces a novel approach to interpreting LLMs by applying inverse reinforcement learning (IRL) to recover their implicit reward functions.
We conduct experiments on toxicity-aligned LLMs of varying sizes, extracting reward models that achieve up to 80.40% accuracy in predicting human preferences.
arXiv Detail & Related papers (2024-10-16T12:14:25Z) - Zero-shot Model-based Reinforcement Learning using Large Language Models [12.930241182192988]
We investigate how pre-trained Large Language Models can be leveraged to predict in context the dynamics of continuous Markov decision processes.
We present proof-of-concept applications in two reinforcement learning settings: model-based policy evaluation and data-augmented off-policy reinforcement learning.
arXiv Detail & Related papers (2024-10-15T15:46:53Z) - LLM In-Context Recall is Prompt Dependent [0.0]
A model's ability to do this significantly influences its practical efficacy and dependability in real-world applications.
This study demonstrates that an LLM's recall capability is not only contingent upon the prompt's content but also may be compromised by biases in its training data.
arXiv Detail & Related papers (2024-04-13T01:13:59Z) - Comprehensive Reassessment of Large-Scale Evaluation Outcomes in LLMs: A Multifaceted Statistical Approach [64.42462708687921]
Evaluations have revealed that factors such as scaling, training types, architectures and other factors profoundly impact the performance of LLMs.
Our study embarks on a thorough re-examination of these LLMs, targeting the inadequacies in current evaluation methods.
This includes the application of ANOVA, Tukey HSD tests, GAMM, and clustering technique.
arXiv Detail & Related papers (2024-03-22T14:47:35Z) - How Can LLM Guide RL? A Value-Based Approach [68.55316627400683]
Reinforcement learning (RL) has become the de facto standard practice for sequential decision-making problems by improving future acting policies with feedback.
Recent developments in large language models (LLMs) have showcased impressive capabilities in language understanding and generation, yet they fall short in exploration and self-improvement capabilities.
We develop an algorithm named LINVIT that incorporates LLM guidance as a regularization factor in value-based RL, leading to significant reductions in the amount of data needed for learning.
arXiv Detail & Related papers (2024-02-25T20:07:13Z) - Rethinking the Roles of Large Language Models in Chinese Grammatical
Error Correction [62.409807640887834]
Chinese Grammatical Error Correction (CGEC) aims to correct all potential grammatical errors in the input sentences.
LLMs' performance as correctors on CGEC remains unsatisfactory due to its challenging task focus.
We rethink the roles of LLMs in the CGEC task so that they can be better utilized and explored in CGEC.
arXiv Detail & Related papers (2024-02-18T01:40:34Z) - C-ICL: Contrastive In-context Learning for Information Extraction [54.39470114243744]
c-ICL is a novel few-shot technique that leverages both correct and incorrect sample constructions to create in-context learning demonstrations.
Our experiments on various datasets indicate that c-ICL outperforms previous few-shot in-context learning methods.
arXiv Detail & Related papers (2024-02-17T11:28:08Z) - Rethinking Machine Unlearning for Large Language Models [85.92660644100582]
We explore machine unlearning in the domain of large language models (LLMs)
This initiative aims to eliminate undesirable data influence (e.g., sensitive or illegal information) and the associated model capabilities.
arXiv Detail & Related papers (2024-02-13T20:51:58Z) - Towards LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Models [56.34029644009297]
Large language models (LLMs) have demonstrated the ability to overcome various limitations of formal Knowledge Representation (KR) systems.
LLMs excel most in abductive reasoning, followed by deductive reasoning, while they are least effective at inductive reasoning.
We study single-task training, multi-task training, and "chain-of-thought" knowledge distillation fine-tuning technique to assess the performance of model.
arXiv Detail & Related papers (2023-10-02T01:00:50Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.