Resist and Update: Counterfactual Report Coordinates for Incentive-Compatible LLMs

• URL: http://arxiv.org/abs/2607.12985v2
• Date: Tue, 21 Jul 2026 08:33:51 GMT
• Title: Resist and Update: Counterfactual Report Coordinates for Incentive-Compatible LLMs
• Abstract summary: Aligned language models routinely misreport under non-evidential pressure.<n>We study the two demands, resist (ignore forbidden pressure) and update (follow licensed evidence)<n>We causally localize low-rank report coordinates for answer, confidence, and caveat.
• Score: 4.721990925113432
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Aligned language models routinely misreport under non-evidential pressure: they cave to a confident user, yet fail to revise when genuine evidence arrives. We cast this as a failure of internal incentive-compatibility and study the two demands, resist (ignore forbidden pressure) and update (follow licensed evidence), on a Bayesian-witness benchmark with known posteriors, where the same user disagreement is evidence or pressure purely by stated source reliability, removing the evidence/pressure confound by construction. Using interchange interventions rather than probes, we causally localize low-rank report coordinates for answer, confidence, and caveat, establishing causal sufficiency at a late intervention site rather than uniqueness or necessity, with a causal cross-talk matrix showing strong own-coordinate control and only small cross-effects (partial functional disentanglement). We then introduce a training-free counterfactual report-coordinate (CRC) clamp that references the model's own report under an incentive-neutralized counterfactual of the prompt. The two-pass full-window clamp attains resist and update of $1.00$ jointly (Wilson 95% CI $[0.99,1.00]$; the rank-16 projection alone reaches $0.88/0.90$), which we read as a causal certificate and upper bound under a constructible reference, not a claim of a deployed solution. Tested global decoding and fixed-direction steering trade one objective against the other, and resist-only training collapses updating to $0.01$. The deployable single-pass compilation is lossy ($0.73/0.97$). The mechanism and the clamp reproduce across three model families and transfer to a natural sycophancy benchmark with significant paired improvements. Our contribution is the interface and certification method: activation-level counterfactual incentive-invariance as a structural primitive for internal incentive-compatibility.

Related papers

• Not All Relations Are Equal: Relation-Balanced and Calibrated Graph Learning for Provenance-Based Intrusion Detection [66.44527094471619]
  We present RECAL, an unsupervised framework using relation-balanced masked graph learning to better capture rare interaction patterns.<n>On three DARPA E3 datasets, RECAL achieves F1 scores of 99.99%, 99.93%, and 99.99%, outperforming the best baseline on each dataset by 0.88, 0.82, and 0.42 percentage points, respectively.
  arXiv  Detail & Related papers  (2026-09-15T00:31:01Z)
• Principled Detection of Coordinated Manipulation from Aggregate Distortion and Account Reuse [10.023638697449062]
  Coordinated manipulation is collective: plausible accounts can jointly distort ratings, rankings, and engagement.<n>We introduce an aggregate-first evidence layer that treats distortion of a context-level outcome distribution as the primary evidence object.<n>We evaluate the mechanism with controlled rotation experiments and paired counterfactual interventions on historical Amazon review streams.
  arXiv  Detail & Related papers  (2026-09-11T18:16:42Z)
• Repeated-Game Security for Restaking-Based Verifiable Inference [2.9661360665913574]
  This paper shows that a one-round slashing condition can overstate security when inference is supplied repeatedly under the same stake.<n>We propose a deployable mechanism combining history-dependent challenges, reputation-weighted slashing, and stake vesting.
  arXiv  Detail & Related papers  (2026-08-10T03:03:56Z)
• CausalNav: Reliability-Certified Causal World Models for Control under Physical-Parameter Shift [4.0604823050005345]
  CausalNav is a controller built around a signed, action-conditioned transition graph over identified state coordinates.<n>At deployment CausalNav simulates a small library of intervention sequences, converts their objective error into policy-logit advice.<n>We evaluate against nine controlled baselines on CartPole-v1 and discretized Pendulum-v1.
  arXiv  Detail & Related papers  (2026-08-07T23:16:57Z)
• Does Reasoning Preserve Alignment? On the Trustworthiness of Large Reasoning Models [55.788110316999166]
  We compare reasoning models produced via supervised fine-tuning, RL-based post-training, and distillation against instruction-tuned baselines.<n>We observe that reasoning models often improve on reasoning benchmarks but exhibit alignment regressions.<n>These regressions are consistent with behavioral drift from the instruction-tuned baseline, measured by KL divergence.
  arXiv  Detail & Related papers  (2026-06-09T16:14:27Z)
• Trust, but Don't Verify: Epistemic Blind Spots in LLM Source Evaluation [0.0]
  We show that models possess the capability to detect fabricated statistics but do not recruit this capability during multi-source synthesis.<n>Specifically, source influence is governed by a methodology-register gate that responds to the distributional register of analytical text but not to numeric validity.
  arXiv  Detail & Related papers  (2026-06-03T20:15:48Z)
• SAGE: Shaping Anchors for Guided Exploration in RLVR of LLMs [55.46289074417954]
  reinforcement learning with verifiable rewards (RLVR) reliably improves pass@1 on reasoning tasks, yet often fails to yield comparable gains in pass@k.<n>We argue that a central structural constraint arises from reverse-KL regularization, which stabilizes training but inherently anchors the policy to the reference distribution.<n>We propose SAGE, a principled framework that enables controllable empirical support expansion by reshaping the reverse-KL anchor distribution itself.
  arXiv  Detail & Related papers  (2026-05-15T07:42:21Z)
• MEMSAD: Gradient-Coupled Anomaly Detection for Memory Poisoning in Retrieval-Augmented Agents [0.0]
  We formalize memory poisoning attacks on retrieval-augmented agents as a Stackelberg game with a unified evaluation framework.<n>We show faithful evaluation increases measured attack success by $4times$ (ASR-R: 0.25 to 1.00$)<n>Our primary contribution is MEMSAD, a calibration-based defense grounded in a gradient coupling.
  arXiv  Detail & Related papers  (2026-05-05T08:15:41Z)
• Trust but Verify: Introducing DAVinCI -- A Framework for Dual Attribution and Verification in Claim Inference for Language Models [53.279391576560755]
  Large Language Models (LLMs) have demonstrated remarkable fluency and versatility across a wide range of NLP tasks, yet they remain prone to factual inaccuracies and limitation.<n>This poses significant risks in high-stakes domains such as healthcare, law, and scientific communication, where trust and verifiability are paramount.<n>We introduce DAVinCI - a Dual Attribution and Verification framework designed to enhance the factual reliability and interpretability of LLM outputs.
  arXiv  Detail & Related papers  (2026-04-23T01:37:50Z)
• The Illusion of Certainty: Decoupling Capability and Calibration in On-Policy Distillation [67.26315138466312]
  We propose a calibration-aware OPD framework, CaOPD, that estimates empirical confidence from model rollouts.<n>Our findings highlight that capability distillation does not imply confidence, and that confidence should be treated as an essential objective in post-training.
  arXiv  Detail & Related papers  (2026-04-18T04:43:40Z)
• Preregistered Belief Revision Contracts [2.28438857884398]
  We introduce PBRC (Preregistered Belief Revision Contracts), a protocol-level mechanism that separates open communication from admissible change.<n>A PBRC contract publicly fixes first-order evidence triggers, admissible revision operators, a priority rule, and a fallback policy.<n>We show that auditable trigger protocols admit evidential PBRC normal forms that preserve belief trajectories and canonicalized audit traces.
  arXiv  Detail & Related papers  (2026-04-16T22:22:54Z)
• FACT-E: Causality-Inspired Evaluation for Trustworthy Chain-of-Thought Reasoning [49.65751420291115]
  Chain-of-Thought (CoT) prompting has improved LLM reasoning, but models often generate explanations that appear coherent while containing unfaithful intermediate steps.<n>We propose FACT-E, a causality-inspired framework for evaluating CoT quality.<n>We show that FACT-E improves reasoning-trajectory selection and yields stronger in-context learnings.
  arXiv  Detail & Related papers  (2026-04-12T15:35:08Z)
• Toward Faithful Segmentation Attribution via Benchmarking and Dual-Evidence Fusion [4.726028690278432]
  We introduce a reproducible benchmark that tests intervention-based faithfulness, off-target leakage, runtime, and on Pascal VOC.<n>We propose Dual-Evidence Attribution (DEA), a lightweight correction that fuses evidence with region-level intervention signals.
  arXiv  Detail & Related papers  (2026-03-23T22:52:00Z)
• Information Fidelity in Tool-Using LLM Agents: A Martingale Analysis of the Model Context Protocol [69.11739400975445]
  We introduce the first theoretical framework for analyzing error accumulation in Model Context Protocol (MCP) agents.<n>We show that cumulative distortion exhibits linear growth and high-probability deviations bounded by $O(sqrtT)$.<n>Key findings include: semantic weighting reduces distortion by 80%, and periodic re-grounding approximately every 9 steps suffices for error control.
  arXiv  Detail & Related papers  (2026-02-10T21:08:53Z)
• Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers [90.50039419576807]
  Reinforcement Learning with Verifiable Rewards (RLVR) trains policies against automated verifiers to avoid costly human labeling.<n>To reduce vulnerability to verifier hacking, many RLVR systems collapse rewards to binary $0,1$ during training.<n>This choice carries a cost: it introduces textitfalse negatives (rejecting correct answers, FNs) and textitfalse positives (accepting incorrect ones, FPs)
  arXiv  Detail & Related papers  (2025-10-01T13:56:44Z)
• Trusted Uncertainty in Large Language Models: A Unified Framework for Confidence Calibration and Risk-Controlled Refusal [31.458406135473805]
  We present UniCR, a unified framework that turns heterogeneous uncertainty evidence into a calibrated probability of correctness.<n>UniCR learns a lightweight calibration head with temperature scaling and proper scoring.<n>Experiments on short-form QA, code generation with execution tests, and retrieval-augmented long-form QA show consistent improvements in calibration metrics.
  arXiv  Detail & Related papers  (2025-09-01T13:14:58Z)
• TrustLoRA: Low-Rank Adaptation for Failure Detection under Out-of-distribution Data [62.22804234013273]
  We propose a simple failure detection framework to unify and facilitate classification with rejection under both covariate and semantic shifts.<n>Our key insight is that by separating and consolidating failure-specific reliability knowledge with low-rank adapters, we can enhance the failure detection ability effectively and flexibly.
  arXiv  Detail & Related papers  (2025-04-20T09:20:55Z)
• Explicit Tradeoffs between Adversarial and Natural Distributional Robustness [48.44639585732391]
  In practice, models need to enjoy both types of robustness to ensure reliability. In this work, we show that in fact, explicit tradeoffs exist between adversarial and natural distributional robustness.
  arXiv  Detail & Related papers  (2022-09-15T19:58:01Z)

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.