REALISTA optimizes continuous combinations of valid editing directions in latent space to produce realistic adversarial prompts that elicit hallucinations more effectively than prior methods, including on large reasoning models.
super hub Mixed citations
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Mixed citation behavior. Most common role is background (50%).
136
Pith papers citing it
Background
50% of classified citations
abstract
We explore how generating a chain of thought -- a series of intermediate reasoning steps -- significantly improves the ability of large language models to perform complex reasoning. In particular, we show how such reasoning abilities emerge naturally in sufficiently large language models via a simple method called chain of thought prompting, where a few chain of thought demonstrations are provided as exemplars in prompting. Experiments on three large language models show that chain of thought prompting improves performance on a range of arithmetic, commonsense, and symbolic reasoning tasks. The empirical gains can be striking. For instance, prompting a 540B-parameter language model with just eight chain of thought exemplars achieves state of the art accuracy on the GSM8K benchmark of math word problems, surpassing even finetuned GPT-3 with a verifier.
hub tools
citation-role summary
background 3
method 3
citation-polarity summary
claims ledger
- abstract We explore how generating a chain of thought -- a series of intermediate reasoning steps -- significantly improves the ability of large language models to perform complex reasoning. In particular, we show how such reasoning abilities emerge naturally in sufficiently large language models via a simple method called chain of thought prompting, where a few chain of thought demonstrations are provided as exemplars in prompting. Experiments on three large language models show that chain of thought prompting improves performance on a range of arithmetic, commonsense, and symbolic reasoning tasks. Th
authors
co-cited works
representative citing papers
LLM activations encode current and prior entities in orthogonal slots, but models only use the current slot for explicit factual retrieval despite prior-slot information being linearly decodable.
Looped transformers with recall and outer normalization produce reachable, input-dependent fixed points with stable gradients, enabling generalization, while those without recall cannot; a new internal recall variant performs competitively or better.
GIANTS-4B, trained with RL on a new 17k-example benchmark of parent-to-child paper insights, achieves 34% relative improvement over gemini-3-pro in LM-judge similarity and is rated higher-impact by a citation predictor.
Long-range dependency in integer multiplication is a mirage from 1D representation; a 2D grid reduces it to local 3x3 operations, letting a 321-parameter neural cellular automaton generalize perfectly to inputs 683 times longer than training while Transformers fail.
DSPy compiles short declarative programs into LM pipelines that self-optimize and outperform both standard few-shot prompting and expert-written chains on math, retrieval, and QA tasks.
Tree of Thoughts enables language models to solve complex planning tasks by generating, evaluating, and searching over coherent intermediate thoughts in a tree, raising Game of 24 success from 4% to 74% with GPT-4.
Generative agents with memory streams, reflection, and planning using LLMs exhibit believable individual and emergent social behaviors in a simulated town.
GPT-4-generated instruction data produces superior zero-shot performance in finetuned LLaMA models versus prior state-of-the-art data.
Grokking arises from gradual amplification of a Fourier-based circuit in the weights followed by removal of memorizing components.
Language models generate robot policy code from natural language commands via few-shot prompting, enabling spatial-geometric reasoning, generalization, and precise control on real robots.
RAPO uses an information-theoretic lower bound on visual gain to select high-entropy reflection anchors and optimizes a chain-masked KL surrogate, delivering gains over baselines on reasoning benchmarks across LVLM backbones.
Frontier LLMs achieve 95-100% accuracy on AMC/AIME problems but recover far fewer distinct valid strategies than human references, while collectively generating 50 novel strategies.
CA-SQL achieves 51.72% execution accuracy on the challenging tier of the BIRD benchmark using GPT-4o-mini by scaling exploration breadth according to estimated task difficulty, evolutionary prompt seeding, and candidate voting.
vOPD stabilizes on-policy distillation gradients by subtracting a closed-form per-token negative reverse KL baseline as a detached control variate, preserving unbiasedness while lowering variance and matching expensive full-vocabulary methods.
RL training compute for logical reasoning follows a power law in proof depth whose exponent rises with logic expressiveness, and more expressive training yields larger gains on downstream benchmarks.
TRIP-Evaluate is a new open multimodal benchmark with 837 text, image, and point-cloud items organized by a role-task-knowledge taxonomy to evaluate large models on transportation workflows.
XGRAG uses graph perturbations to quantify component contributions in GraphRAG and achieves 14.81% better explanation quality than text-based baselines on QA datasets, with correlations to graph centrality.
RAG-Reflect achieves F1=0.78 on valid comment-edit prediction using retrieval-augmented reasoning and self-reflection, outperforming baselines and approaching fine-tuned models without retraining.
R2IF improves LLM function-calling accuracy by up to 34.62% on BFCL using a composite reward system with CER and SMV components optimized via GRPO, while increasing interpretability through positive CoT effectiveness.
HiPO improves LLM reasoning performance by optimizing preferences separately on response segments rather than entire outputs.
The conceptual multiverse system with a verification framework for decision structures helps users in philosophy, AI alignment, and poetry build clearer working maps of open-ended problems by making implicit LLM choices explicit and changeable.
RAGognizer adds a detection head to LLMs for joint training on generation and token-level hallucination detection, yielding SOTA detection and fewer hallucinations in RAG while preserving output quality.
SAT trains multi-LLM teams with sequential block updates to deliver monotonic gains and plug-and-play model swaps that provably improve performance bounds.
citing papers explorer
-
REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations
REALISTA optimizes continuous combinations of valid editing directions in latent space to produce realistic adversarial prompts that elicit hallucinations more effectively than prior methods, including on large reasoning models.
-
Slot Machines: How LLMs Keep Track of Multiple Entities
LLM activations encode current and prior entities in orthogonal slots, but models only use the current slot for explicit factual retrieval despite prior-slot information being linearly decodable.
-
Stability and Generalization in Looped Transformers
Looped transformers with recall and outer normalization produce reachable, input-dependent fixed points with stable gradients, enabling generalization, while those without recall cannot; a new internal recall variant performs competitively or better.
-
GIANTS: Generative Insight Anticipation from Scientific Literature
GIANTS-4B, trained with RL on a new 17k-example benchmark of parent-to-child paper insights, achieves 34% relative improvement over gemini-3-pro in LM-judge similarity and is rated higher-impact by a citation predictor.
-
On the Mirage of Long-Range Dependency, with an Application to Integer Multiplication
Long-range dependency in integer multiplication is a mirage from 1D representation; a 2D grid reduces it to local 3x3 operations, letting a 321-parameter neural cellular automaton generalize perfectly to inputs 683 times longer than training while Transformers fail.
-
DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines
DSPy compiles short declarative programs into LM pipelines that self-optimize and outperform both standard few-shot prompting and expert-written chains on math, retrieval, and QA tasks.
-
Tree of Thoughts: Deliberate Problem Solving with Large Language Models
Tree of Thoughts enables language models to solve complex planning tasks by generating, evaluating, and searching over coherent intermediate thoughts in a tree, raising Game of 24 success from 4% to 74% with GPT-4.
-
Generative Agents: Interactive Simulacra of Human Behavior
Generative agents with memory streams, reflection, and planning using LLMs exhibit believable individual and emergent social behaviors in a simulated town.
-
Instruction Tuning with GPT-4
GPT-4-generated instruction data produces superior zero-shot performance in finetuned LLaMA models versus prior state-of-the-art data.
-
Progress measures for grokking via mechanistic interpretability
Grokking arises from gradual amplification of a Fourier-based circuit in the weights followed by removal of memorizing components.
-
Code as Policies: Language Model Programs for Embodied Control
Language models generate robot policy code from natural language commands via few-shot prompting, enabling spatial-geometric reasoning, generalization, and precise control on real robots.
-
Reflection Anchors for Propagation-Aware Visual Retention in Long-Chain Multimodal Reasoning
RAPO uses an information-theoretic lower bound on visual gain to select high-entropy reflection anchors and optimizes a chain-masked KL surrogate, delivering gains over baselines on reasoning benchmarks across LVLM backbones.
-
Beyond Accuracy: Evaluating Strategy Diversity in LLM Mathematical Reasoning
Frontier LLMs achieve 95-100% accuracy on AMC/AIME problems but recover far fewer distinct valid strategies than human references, while collectively generating 50 novel strategies.
-
CA-SQL: Complexity-Aware Inference Time Reasoning for Text-to-SQL via Exploration and Compute Budget Allocation
CA-SQL achieves 51.72% execution accuracy on the challenging tier of the BIRD benchmark using GPT-4o-mini by scaling exploration breadth according to estimated task difficulty, evolutionary prompt seeding, and candidate voting.
-
KL for a KL: On-Policy Distillation with Control Variate Baseline
vOPD stabilizes on-policy distillation gradients by subtracting a closed-form per-token negative reverse KL baseline as a detached control variate, preserving unbiasedness while lowering variance and matching expensive full-vocabulary methods.
-
Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Key
RL training compute for logical reasoning follows a power law in proof depth whose exponent rises with logic expressiveness, and more expressive training yields larger gains on downstream benchmarks.
-
TRIP-Evaluate: An Open Multimodal Benchmark for Evaluating Large Models in Transportation
TRIP-Evaluate is a new open multimodal benchmark with 837 text, image, and point-cloud items organized by a role-task-knowledge taxonomy to evaluate large models on transportation workflows.
-
XGRAG: A Graph-Native Framework for Explaining KG-based Retrieval-Augmented Generation
XGRAG uses graph perturbations to quantify component contributions in GraphRAG and achieves 14.81% better explanation quality than text-based baselines on QA datasets, with correlations to graph centrality.
-
RAG-Reflect: Agentic Retrieval-Augmented Generation with Reflections for Comment-Driven Code Maintenance on Stack Overflow
RAG-Reflect achieves F1=0.78 on valid comment-edit prediction using retrieval-augmented reasoning and self-reflection, outperforming baselines and approaching fine-tuned models without retraining.
-
R2IF: Aligning Reasoning with Decisions via Composite Rewards for Interpretable LLM Function Calling
R2IF improves LLM function-calling accuracy by up to 34.62% on BFCL using a composite reward system with CER and SMV components optimized via GRPO, while increasing interpretability through positive CoT effectiveness.
-
HiPO: Hierarchical Preference Optimization for Adaptive Reasoning in LLMs
HiPO improves LLM reasoning performance by optimizing preferences separately on response segments rather than entire outputs.
-
Navigating the Conceptual Multiverse
The conceptual multiverse system with a verification framework for decision structures helps users in philosophy, AI alignment, and poetry build clearer working maps of open-ended problems by making implicit LLM choices explicit and changeable.
-
RAGognizer: Hallucination-Aware Fine-Tuning via Detection Head Integration
RAGognizer adds a detection head to LLMs for joint training on generation and token-level hallucination detection, yielding SOTA detection and fewer hallucinations in RAG while preserving output quality.
-
SAT: Sequential Agent Tuning for Coordinator Free Plug and Play Multi-LLM Training with Monotonic Improvement Guarantees
SAT trains multi-LLM teams with sequential block updates to deliver monotonic gains and plug-and-play model swaps that provably improve performance bounds.
-
IE as Cache: Information Extraction Enhanced Agentic Reasoning
IE-as-Cache framework repurposes information extraction as a dynamic cognitive cache to improve agentic reasoning accuracy in LLMs on challenging benchmarks.
-
CapTalk: Unified Voice Design for Single-Utterance and Dialogue Speech Generation
CapTalk unifies single-utterance and dialogue voice design via utterance- and speaker-level captions plus a hierarchical variational module for stable timbre with adaptive expression.
-
An End-to-End Approach for Fixing Concurrency Bugs via SHB-Based Context Extractor
ConFixAgent repairs diverse concurrency bugs end-to-end by using Static Happens-Before graphs to extract relevant code context for LLMs, outperforming prior tools in benchmarks.
-
Profile-Then-Reason: Bounded Semantic Complexity for Tool-Augmented Language Agents
PTR framework profiles a workflow upfront then executes it deterministically with bounded verification and repair, limiting LM calls to 2-3 while outperforming ReAct in 16 of 24 tested configurations.
-
Unlocking Prompt Infilling Capability for Diffusion Language Models
Full-sequence masking in SFT unlocks prompt infilling for masked diffusion language models, producing templates that match or surpass hand-designed ones and transfer across models.
-
Trivial Vocabulary Bans Improve LLM Reasoning More Than Deep Linguistic Constraints
Banning filler words like 'very' and 'just' improved LLM reasoning by 6.7 percentage points while E-Prime improved it by only 3.7, with gains ranking in exact inverse order of theoretical depth across models and tasks.
-
Internalized Reasoning for Long-Context Visual Document Understanding
A synthetic pipeline creates and internalizes reasoning traces in VLMs for long-context visual document understanding, with a 32B model surpassing a 235B model on MMLongBenchDoc and showing 12.4x fewer output tokens.
-
BACE: LLM-based Code Generation through Bayesian Anchored Co-Evolution of Code and Test Populations
BACE reformulates LLM code synthesis as Bayesian co-evolution of code and test populations anchored on minimal public examples, achieving superior performance on LiveCodeBench v6.
-
GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models
LLMs display high variance and major accuracy drops on GSM-Symbolic variants of grade-school math problems, indicating they replicate training patterns rather than execute logical reasoning.
-
Large Language Models as Optimizers
Large language models can optimize by being prompted with histories of past solutions and scores to propose better ones, producing prompts that raise accuracy up to 8% on GSM8K and 50% on Big-Bench Hard over human-designed baselines.
-
VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models
VoxPoser uses LLMs to compose 3D value maps via VLM interaction for model-based synthesis of robust robot trajectories on open-set language-specified manipulation tasks.
-
Let's Verify Step by Step
Process supervision significantly outperforms outcome supervision for training models on the MATH dataset, achieving 78% accuracy on a representative test subset with active learning and a released 800k step-label dataset.
-
Voyager: An Open-Ended Embodied Agent with Large Language Models
Voyager achieves superior lifelong learning in Minecraft by combining an automatic exploration curriculum, a library of executable skills, and iterative LLM prompting with environment feedback, yielding 3.3x more unique items and 15.3x faster milestone unlocks than prior methods while generalizing技能
-
Reflexion: Language Agents with Verbal Reinforcement Learning
Reflexion lets LLM agents improve via stored verbal reflections on task feedback, reaching 91% pass@1 on HumanEval and outperforming prior GPT-4 results.
-
Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
SayCan combines an LLM's high-level semantic knowledge with robot skill value functions to select only feasible actions, enabling completion of abstract natural-language instructions on a real mobile manipulator.
-
RTLC -- Research, Teach-to-Learn, Critique: A three-stage prompting paradigm inspired by the Feynman Learning Technique that lifts LLM-as-judge accuracy on JudgeBench with no fine-tuning
RTLC prompting lifts Claude 3.7 Sonnet pairwise accuracy on 350 hard JudgeBench items from 64.6% to 78.6% via a Research-Teach-Critique scaffold that beats self-consistency.
-
Nice Fold or Hero Call: Learning Budget-Efficient Thinking for Adaptive Reasoning
BET reduces reasoning tokens by about 55% on average while improving performance across benchmarks by learning to short-solve easy queries, fold early on unsolvable ones, and preserve budget for hard solvable queries.
-
From Controlled to the Wild: Evaluation of Pentesting Agents for the Real-World
A practical evaluation protocol for AI pentesting agents that uses validated vulnerability discovery, LLM semantic matching, and bipartite scoring to assess performance in realistic, complex targets.
-
Continuous Latent Contexts Enable Efficient Online Learning in Transformers
Transformers equipped with continuous latent context tokens can implement foundational online decision-making algorithms such as weighted majority and Q-learning, and a trained small model outperforms larger LLMs on synthetic online prediction tasks.
-
Let the Target Select for Itself: Data Selection via Target-Aligned Paths
Target-aligned data selection via normalized endpoint loss drop on a validation-induced reference path achieves competitive performance with reduced computational overhead.
-
Structured Recurrent Mixers for Massively Parallelized Sequence Generation
Structured Recurrent Mixers enable algebraic switching between parallel training and recurrent inference representations, delivering higher efficiency, information capacity, and throughput than other linear-complexity models.
-
BioTool: A Comprehensive Tool-Calling Dataset for Enhancing Biomedical Capabilities of Large Language Models
BioTool dataset enables fine-tuning a 4B-parameter LLM to outperform GPT-5.1 in biomedical tool calling while improving downstream answer quality per human experts.
-
Hierarchical Visual Agent: Managing Contexts in Joint Image-Text Space for Advanced Chart Reasoning
HierVA improves multi-step chart question answering by having a high-level manager maintain key joint contexts while specialized workers perform targeted reasoning with visual zoom-in.
-
Atomic Fact-Checking Increases Clinician Trust in Large Language Model Recommendations for Oncology Decision Support: A Randomized Controlled Trial
Atomic fact-checking of LLM oncology recommendations increased clinician trust from 26.9% to 66.5% (Cohen's d=0.94) in a trial of 356 doctors.
-
Spatiotemporal Hidden-State Dynamics as a Signature of Internal Reasoning in Large Language Models
Large reasoning models show measurable hidden-state dynamics that a new statistic can use to distinguish correct reasoning trajectories without labels.
-
Compared to What? Baselines and Metrics for Counterfactual Prompting
Counterfactual prompting effects on LLMs are often indistinguishable from those caused by meaning-preserving paraphrases, causing most previously reported demographic sensitivities to disappear under proper statistical comparison.