DeLTa: A Decoding Strategy based on Logit Trajectory Prediction Improves Factuality and Reasoning Ability
- URL: http://arxiv.org/abs/2503.02343v1
- Date: Tue, 04 Mar 2025 07:07:17 GMT
- Title: DeLTa: A Decoding Strategy based on Logit Trajectory Prediction Improves Factuality and Reasoning Ability
- Authors: Yunzhen He, Yusuke Takase, Yoichi Ishibashi, Hidetoshi Shimodaira,
- Abstract summary: This paper proposes a novel decoding strategy aimed at enhancing both factual accuracy and inferential reasoning.<n>Our approach adjusts next-token probabilities by analyzing the trajectory of logits from lower to higher layers in Transformers.<n> Experiments on TruthfulQA demonstrate that DeLTa attains up to a 4.9% improvement over the baseline.
- Score: 3.2561294196141835
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Large Language Models (LLMs) are increasingly being used in real-world applications. However, concerns about the reliability of the content they generate persist, as it frequently deviates from factual correctness or exhibits deficiencies in logical reasoning. This paper proposes a novel decoding strategy aimed at enhancing both factual accuracy and inferential reasoning without requiring any modifications to the architecture or pre-trained parameters of LLMs. Our approach adjusts next-token probabilities by analyzing the trajectory of logits from lower to higher layers in Transformers and applying linear regression. We find that this Decoding by Logit Trajectory-based approach (DeLTa) effectively reinforces factuality and reasoning while mitigating incorrect generation. Experiments on TruthfulQA demonstrate that DeLTa attains up to a 4.9% improvement over the baseline. Furthermore, it enhances performance by up to 8.1% on StrategyQA and 7.3% on GSM8K, both of which demand strong reasoning capabilities.
Related papers
- Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes [16.451488374845407]
We present a novel framework addressing a critical vulnerability in Large Language Models (LLMs)<n>This phenomenon poses substantial risks in high-stakes domains including healthcare, legal analysis, and scientific research.
arXiv Detail & Related papers (2025-07-25T10:34:51Z) - Learning Efficient and Generalizable Graph Retriever for Knowledge-Graph Question Answering [75.12322966980003]
Large Language Models (LLMs) have shown strong inductive reasoning ability across various domains.<n>Most existing RAG pipelines rely on unstructured text, limiting interpretability and structured reasoning.<n>Recent studies have explored integrating knowledge graphs with LLMs for knowledge graph question answering.<n>We propose RAPL, a novel framework for efficient and effective graph retrieval in KGQA.
arXiv Detail & Related papers (2025-06-11T12:03:52Z) - Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback [59.078756231841574]
Critique-GRPO is an online RL framework that integrates both natural language and numerical feedback for effective policy optimization.<n>We show Critique-GRPO consistently outperforms supervised learning and RL-based fine-tuning methods across eight challenging mathematical, STEM, and general reasoning tasks.
arXiv Detail & Related papers (2025-06-03T17:39:02Z) - Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens [51.90059610606049]
This paper revisits the efficiency of such reasoning processes through an information-theoretic lens.<n>We propose two metrics, InfoBias and InfoGain, to quantify divergence from ideal reasoning paths and stepwise information contribution.<n>Motivated by these findings, we introduce an entropy-based Adaptive Think strategy that dynamically halts reasoning once confidence is sufficiently high.
arXiv Detail & Related papers (2025-05-23T13:38:56Z) - SEAL: Steerable Reasoning Calibration of Large Language Models for Free [58.190800043449336]
Large Language Models (LLMs) have demonstrated compelling capabilities for complex reasoning tasks via the extended chain-of-thought (CoT) reasoning mechanism.
Recent studies reveal substantial redundancy in the CoT reasoning traces, which negatively impacts model performance.
We introduce SEAL, a training-free approach that seamlessly calibrates the CoT process, improving accuracy while demonstrating significant efficiency gains.
arXiv Detail & Related papers (2025-04-07T02:42:07Z) - R-PRM: Reasoning-Driven Process Reward Modeling [53.06844294668382]
Process Reward Models (PRMs) have emerged as a promising solution by evaluating each reasoning step.
Existing PRMs typically output evaluation scores directly, limiting both learning efficiency and evaluation accuracy.
We propose Reasoning-Driven Process Reward Modeling (R-PRM)
R-PRM generates seed data from limited annotations, effectively bootstrapping our model's reasoning capabilities.
arXiv Detail & Related papers (2025-03-27T09:23:08Z) - FAIT: Fault-Aware Fine-Tuning for Better Code Generation [11.8755180563981]
We propose Fault-Aware Fine-Tuning (FAIT) to enhance instruction-tuned large language models' code generation.
Our method achieves an average relative improvement of 6.9% on pass@1 with just one epoch of training.
Some enhanced 6.7B LLMs outperforming closed-source models, e.g., GPT-3.5-Turbo.
arXiv Detail & Related papers (2025-03-21T07:23:26Z) - Recursive Decomposition of Logical Thoughts: Framework for Superior Reasoning and Knowledge Propagation in Large Language Models [1.4956870931936515]
We introduce RDoLT, a novel framework that significantly boosts Large Language Models reasoning performance.<n>RDoLT is built on three key innovations: (1) breaking down complex reasoning tasks into sub-tasks of progressive complexity; (2) employing an advanced selection and scoring mechanism to identify the most promising reasoning thoughts; and (3) integrating a knowledge propagation module that mimics human learning.<n>Our approach was evaluated across multiple benchmarks, including GSM8K, SVAMP, MultiArithm, LastLetterConcatenation, and Gaokao2023 Math.
arXiv Detail & Related papers (2025-01-03T02:55:44Z) - Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-Rewarding [74.31981011985681]
Large language models (LLMs) have shown impressive capabilities, but still struggle with complex reasoning tasks requiring multiple steps.
We introduce LaTent Reasoning Optimization (LaTRO), a principled framework that formulates reasoning as sampling from a latent distribution.
We validate LaTRO through experiments on GSM8K and ARC-Challenge datasets using multiple model architectures.
arXiv Detail & Related papers (2024-11-06T22:02:30Z) - UncertaintyRAG: Span-Level Uncertainty Enhanced Long-Context Modeling for Retrieval-Augmented Generation [93.38604803625294]
We present UncertaintyRAG, a novel approach for long-context Retrieval-Augmented Generation (RAG)
We use Signal-to-Noise Ratio (SNR)-based span uncertainty to estimate similarity between text chunks.
UncertaintyRAG outperforms baselines by 2.03% on LLaMA-2-7B, achieving state-of-the-art results.
arXiv Detail & Related papers (2024-10-03T17:39:38Z) - Strategic Chain-of-Thought: Guiding Accurate Reasoning in LLMs through Strategy Elicitation [16.350747493026432]
The Chain-of-Thought (CoT) paradigm has emerged as a critical approach for enhancing the reasoning capabilities of large language models (LLMs)
We propose the textbfStrategic Chain-of-Thought (SCoT) to refine LLM performance by integrating strategic knowledge prior to generating intermediate reasoning steps.
SCoT employs a two-stage approach within a single prompt: first eliciting an effective problem-solving strategy, which is then used to guide the generation of high-quality CoT paths and final answers.
arXiv Detail & Related papers (2024-09-05T06:28:05Z) - FFN-SkipLLM: A Hidden Gem for Autoregressive Decoding with Adaptive Feed Forward Skipping [49.66872823080736]
Autoregressive Large Language Models (e.g., LLaMa, GPTs) are omnipresent achieving remarkable success in language understanding and generation.
To mitigate overload incurred during generation, several early-exit and layer-dropping strategies have been proposed.
We propose FFN-SkipLLM, which is an input-adaptive feed-forward skipping strategy.
arXiv Detail & Related papers (2024-04-05T02:35:43Z) - Evidence to Generate (E2G): A Single-agent Two-step Prompting for
Context Grounded and Retrieval Augmented Reasoning [3.117335706912261]
We introduce Evidence to Generate (E2G), a novel single-agent, two-step prompting framework.
Instead of unverified reasoning claims, E2G focuses exclusively on the thought sequences explicitly mentioned in the context.
tool achieves remarkable results robustly across a wide range of knowledge-intensive reasoning and generation tasks.
arXiv Detail & Related papers (2024-01-11T09:49:15Z) - Ladder-of-Thought: Using Knowledge as Steps to Elevate Stance Detection [73.31406286956535]
We introduce the Ladder-of-Thought (LoT) for the stance detection task.
LoT directs the small LMs to assimilate high-quality external knowledge, refining the intermediate rationales produced.
Our empirical evaluations underscore LoT's efficacy, marking a 16% improvement over GPT-3.5 and a 10% enhancement compared to GPT-3.5 with CoT on stance detection task.
arXiv Detail & Related papers (2023-08-31T14:31:48Z)
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.