FROST: Factual Reasoning via Optimized Stochastic Trajectories in Large Language Models during Inference (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing mitigation strategies are needed to improve large language models' reliability and efficiency. |
| Approach: | They propose an inference-time framework that balances exploration andexploitation without additional training or context augmentation. |
| Outcome: | FROST achieves 2–5 percentage point improvements over standard chain-of-thoughtprompting and reduces unsupported outputs by 40% relative to Standard CoT. |
Similar Papers
Drift: Enhancing LLM Faithfulness in Rationale Generation via Dual-Reward Probabilistic Inference (2025.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to improving LLM faithfulness rely on superficial calibration methods or costly retraining. |
| Approach: | They propose a probabilistic inference paradigm that leverages task-specific and lookahead rewards to ensure that LLM-generated rationales are more faithful to model decisions. |
| Outcome: | The proposed model improves both accuracy and faithfulness of Large Language Models (LLMs) on three reasoning tasks. |
HeteroSpec: Leveraging Contextual Heterogeneity for Efficient Speculative Decoding (2026.acl-long)
Copied to clipboard
| Challenge: | Autoregressive decoding limits the inference throughput of Large Language Models due to its sequential dependency. |
| Approach: | They propose a framework that allocates verification effort in proportion to candidate uncertainty. |
| Outcome: | Speculative decoding achieves an average speedup over state-of-the-art methods . a small subset of high-confidence predictions accounts for most successful verifications . |
PretrainRL: Alleviating Factuality Hallucination of Large Language Models at the Beginning (2026.findings-acl)
Copied to clipboard
Langming Liu, Kangtao Lv, Haibin Chen, Weidong Zhang, Yejing Wang, Shilei Liu, Xin Tong, Yujin Yuan, Yongwei Wang, Wenbo Su, Bo Zheng
| Challenge: | Large language models suffer from factual hallucinations where they generate verifiable falsehoods. |
| Approach: | They propose a framework that integrates reinforcement learning into the pretraining phase to consolidate factual knowledge. |
| Outcome: | The proposed framework significantly alleviates factual hallucinations and outperforms state-of-the-art methods. |
NeuroSym-Cal: Bridging the Reasoning-Execution Gap in Code Generation via Hierarchical Calibration (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing calibration methods rely on the assumption that consensus implies correctness . Existing methods fail under systematic errors, leading to miscalibrated high-confidence predictions. |
| Approach: | They propose a hierarchical calibration framework that measures confidence at two levels . they propose sensitivity analysis to measure local curvature of deductive process . |
| Outcome: | The proposed framework de-saturates overconfident errors and improves selective generation performance on OOD benchmarks. |
Temporally Consistent Factuality Probing for Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are used as an alternative knowledge base for many tasks. |
| Approach: | They propose a temporally consistent factuality probe task that extends the consistency probe in the temporal dimension. |
| Outcome: | The proposed task extends the definitions of existing metrics to represent consistent factuality across temporal dimension. |
LEPO: Latent Reasoning Policy Optimization for Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing latent reasoning methods that use chain of thought (CoT) are limited to selecting one discrete token at each reasoning step, which potentially induces information loss. |
| Approach: | They propose a framework that injects controllable stochasticity into latent reasoning via Gumbel-Softmax, restoring LLMs' exploratory capacity and enhancing their compatibility with Reinforcement Learning (RL). |
| Outcome: | The proposed framework preserves richer information for more comprehensive reasoning and is compatible with Reinforcement Learning (RL). |
Accelerated Test-Time Scaling with Model-Free Speculative Sampling (2025.emnlp-main)
Copied to clipboard
Woomin Song, Saket Dingliwal, Sai Muralidhar Jayanthi, Bhavana Ganesh, Jinwoo Shin, Aram Galstyan, Sravan Babu Bodapati
| Challenge: | Language models have demonstrated remarkable capabilities in reasoning tasks through test-time scaling techniques like best-of-N sampling and tree search. |
| Approach: | They propose a model-free speculative decoding approach that exploits redundancy in reasoning trajectories to achieve significant acceleration without compromising accuracy. |
| Outcome: | The proposed approach reduces inference latency by 60-65% while maintaining accuracy. |
Thermometer of Thoughts: Enhancing LLM’s Exploration via Attention Temperature Modulation (2026.acl-long)
Copied to clipboard
| Challenge: | Recent advances in the reasoning capabilities of large language models have enabled them to tackle complex tasks such as mathematics reasoning. |
| Approach: | They propose a method that modulates attention temperature dynamically to shift LLM's internal focus during reasoning, enabling a dynamic shift between exploratory and focused modes. |
| Outcome: | The proposed method improves Pass@10 by 6.78–14.20% and aggregation accuracy by 9.74% across 7 reasoning benchmarks. |
Reasoning Aware Self-Consistency: Leveraging Reasoning Paths for Efficient LLM Sampling (2025.naacl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) generate reasoning paths before answers, but lack a systematic approach to determine optimal number of samples or select the most faithful rationale. |
| Approach: | They propose a framework that evaluates the quality of reasoning and consistency of answers for each generated sample and uses criteria-based stopping and weighted majority voting to guide early stopping decisions and rationale selection. |
| Outcome: | The proposed framework outperforms existing methods while maintaining accuracy. |
SeLaR: Selective Latent Reasoning in Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Recent latent reasoning approaches replace discrete tokens with soft embeddings or hidden states, but they often suffer from two issues: (1) global activation injects perturbations into high-confidence steps, impairing reasoning stability; and (2) soft embeds quickly collapse toward the highest-probability token, limiting exploration of alternative trajectories. |
| Approach: | They propose a lightweight and training-free framework that replaces discrete tokens with soft embeddings or hidden states to address these challenges. |
| Outcome: | Experiments on five reasoning benchmarks show that SeLaR outperforms standard CoT and state-of-the-art training-free methods. |