- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper presents BridgeComp, a prompt compression framework that uses learnable latent tokens and upper-layer attention to pick out the information that really matters for reasoning, while cutting down on lexical-overlap bias. It also adds anchor-conditioned policy optimization to improve token selection, using answer-quality and evidence-preservation rewards. Experiments on multi-hop QA and long-context benchmarks show better downstream accuracy, evidence preservation, and compression efficiency than existing baselines.
Critical strengths
-
Comprehensive experiments and supporting evidence. The paper runs detailed experiments across multiple benchmarks and backs them up with extensive ablations and analyses. The empirical evidence is fairly convincing and supports the effectiveness of the proposed method.
-
Clear writing and good presentation. The paper is well written and easy to follow, with a clear structure and detailed explanations. The figures are also nicely designed—especially Figures 1 and 2, which do a good job of illustrating the motivation and the overall framework.
-
Well-defined problem and motivation. The paper points out meaningful limitations of existing prompt compression methods, especially the loss of reasoning-critical information. The problem is clearly formulated, and the proposed approach is well motivated.
Critical weaknesses
-
Limited methodological novelty. The problem is well defined and the motivation is convincing, but the proposed method mainly brings together existing techniques, namely learnable latent tokens, upper-layer attention aggregation, and RL-based optimization. The overall framework comes across as somewhat of a composite of multiple techniques, so the methodological novelty is relatively limited.
-
Concerns about baseline comparisons and evaluation fairness. It is unclear whether the baselines receive supervision comparable to BridgeComp, which uses additional supervision from gold supporting documents during RL training. Moreover, the efficiency comparisons mostly focus on compression latency rather than end-to-end inference cost. These factors make it difficult to fully assess the performance and efficiency advantages of the proposed method.
Questions for authors
-
What evidence supports the claim that the learned latent tokens capture reasoning-critical information, rather than simply learning better task-specific relevance representations?
-
BridgeComp uses gold supporting-document annotations in its RL rewards. Do the competing baselines have access to comparable supervision, and how much of the performance improvement can be attributed to this additional supervision?
5 comments
Response 2
W2 & Q2. Baseline supervision, its contribution, and end-to-end efficiency
| Training configuration | Supporting-document rewards | HotpotQA EM/F1 | 2Wiki EM/F1 | MuSiQue EM/F1 |
|---|---|---|---|---|
| Full reward | 66.4/80.0 | 64.3/72.8 | 46.3/60.2 | |
| w/o | 63.2/77.3 | 61.8/69.1 | 44.1/58.0 | |
| w/o | 65.3/79.3 | 63.8/71.7 | 46.0/59.6 | |
| Answer-only RL | none | 63.0/77.4 | 62.1/70.2 | 44.0/57.5 |
Table R1. QA performance across reward configurations at . Answer-only RL removes both supporting-document rewards while keeping NTP, AGPG, , and the remaining training settings fixed.
| Method | Compression Rate | Compression (s) | Generation (s) | E2E Latency (s) |
|---|---|---|---|---|
| Original Prompt | - | - | 6.64 | 6.64 |
| AttnComp | 0.5 | 17.32 | 2.22 | 19.55 |
| CPC | 0.5 | 12.89 | 2.12 | 15.02 |
| BridgeComp | 0.5 | 2.12 | 2.12 | 4.24 |
| AttnComp | 0.2 | 14.47 | 1.21 | 15.68 |
| CPC | 0.2 | 11.16 | 1.24 | 12.39 |
| BridgeComp | 0.2 | 1.85 | 1.21 | 3.05 |
Table R2. Compression, generation, and end-to-end latency with 20K document tokens before compression. Generation includes generator prefill and decoding.
Several baselines use additional supervision from gold supporting documents. BRIEF-Pro and CompAct incorporate such supervision during training, though their supervision signals differ from those utilized by BridgeComp. BRIEF-Pro constructs target summaries using gold supporting documents, while CompAct is trained on teacher-generated compression outputs, and completeness judgments from retrieved contexts and distractor contexts. In contrast, BridgeComp incorporates supporting-document annotations into its RL rewards.
Furthermore, we measure how much of the performance improvement can be attributed to this additional supervision. Table R1 quantifies the contribution of the two supporting-document rewards by comparing BridgeComp (i.e., Full reward) and its variant Answer-only RL. The variant “Answer-only RL” removes both rewards while keeping NTP, AGPG, , and the remaining training settings unchanged. Adding two rewards improves EM by 3.4, 2.2, and 2.3 points and F1 by 2.6, 2.6, and 2.7 points on HotpotQA, 2WikiMultihopQA, and MuSiQue, respectively. “Answer-only RL” still outperforms AttnComp on all three datasets, where AttnComp results are reported in Table 1 of the manuscript. On MuSiQue, this variant achieves 44.0/57.5 EM/F1, compared with 38.7/54.4 for AttnComp, retaining gains of 5.3 EM and 3.1 F1 points. Thus, the supporting-document rewards provide additional benefits, while the advantage over AttnComp persists when both rewards are removed.
To fully assess the performance and efficiency advantages of the proposed method, we measure the end-to-end inference cost. Table R2 reports end-to-end latency, which consists of latencies of compression and the complete generator call from prompt submission until the response is finished. We use original retrieved documents with up to 20K tokens before compression to more clearly examine the trade-off between compression overhead and downstream generation latency. BridgeComp reduces total latency from 6.64 seconds for the uncompressed prompt to 4.24 seconds at τ = 0.5 and 3.05 seconds at τ = 0.2, corresponding to reductions of 36.1% and 54.1%, respectively. The downstream generation-time savings therefore exceed the compression cost in this setting. We will incorporate these measurements into Appendix E.
Response 3
Q1. Evidence that latent attention preserves reasoning-critical information
| Backbone LLM | Attention source | Bridging Entity Recall (%) | Evidence-triple Retention (%) |
|---|---|---|---|
| LLaMA3.2-3B | 92.82 | 83.2 | |
| LLaMA3.2-3B | 98.77 | 90.8 | |
| Qwen2.5-7B | 79.66 | 70.6 | |
| Qwen2.5-7B | 96.24 | 91.6 |
Table R3. Bridging Entity Recall and evidence-triple retention on 2WikiMultihopQA at . Within each backbone, the checkpoint, input documents, selected layers, and compression budget are fixed; only the attention source changes.
To distinguish multi-hop bridging preservation from task-specific relevance, we conduct a controlled comparison between question-to-document (i.e., ) and latent-to-document (i.e., ) attention scores on 2WikiMultihopQA at τ = 0.5. Both scoring sources are extracted from the same trained checkpoint under matched compression conditions. Using gold evidence triples provided in 2WikiMultihopQA, we identify intermediate entities in these triples that appear in the input documents but are absent from the query, and evaluate two micro-averaged metrics across the entire test set: (1) Bridging Entity Recall measures the proportion of ground-truth intermediate entities retained after compression; (2) Evidence-triple retention measures the proportion of gold evidence triples that remain semantically supported in the compressed context, evaluated by GPT-6.1-Terra.
As shown in Table R3 above, preserves more annotated intermediate entities and evidence relations than Q→D across both backbones. For LLaMA3.2-3B, improves Bridging Entity Recall by 6.41% (92.82% → 98.77%) and evidence-triple retention by 9.13% (83.2% → 90.8%). For Qwen2.5-7B, the corresponding improvements are 20.81% (79.66% → 96.24%) and 29.75% (70.6% → 91.6%). Because bridging entities have no direct lexical overlap with the question, these gains demonstrate that latent-token attention effectively preserves intermediate entities and relational evidence required for multi-hop inference. In the revised manuscript, we will include this empirical analysis and refine our phrasing to explicitly frame this effect as preserving annotated bridging entities and evidence relations, avoiding any claim that latent tokens explicitly encode identifiable intermediate reasoning steps.
Response 1
Dear Reviewer RyK9
Thank you for your constructive feedback and for recognizing the motivation and empirical evaluation of our work. We clarify BridgeComp’s methodological contribution and present additional controlled experiments addressing supervision fairness, bridging-evidence preservation, and end-to-end efficiency. We will incorporate these clarifications and results into the revised manuscript.
W1. Methodological novelty of BridgeComp
To the best of our knowledge, BridgeComp is the first prompt-compression framework that jointly integrates learnable latent tokens, upper-layer attention aggregation, and anchor-conditioned policy optimization. While individual components have been explored in other domains, adapting and unifying them effectively for budget-constrained prompt compression is nontrivial. Rather than loosely stacking independent modules, BridgeComp couples learned token scoring with policy optimization through a shared latent-to-document attention distribution, which simultaneously defines token importance, the compression anchor, and the exploration policy under a fixed token budget. Our design resolves two mismatches that arise when combining these paradigms naively.
The methodological contribution therefore lies not in the individual components, but in their integration through a shared attention signal that connects learned evidence scoring, budget-constrained token selection, and anchor-relative policy optimization. In the revised manuscript, we will sharpen our presentation in Sections 1 and 3 to make this unified coupling, and its distinction from prior soft-token and unconstrained RL approaches more explicit.